diffs: replace compare controller with new html based diffs:

* side/side + unified support
* redesign of diff changes/operations
* added button to see file before the change
* auto collapses large diffs

refs  #4232

licenses/diff_match_patch_license.txt

@@ -0,0 +1,14 b''
+Copyright 2006 Google Inc.
+http://code.google.com/p/google-diff-match-patch/
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

rhodecode/lib/diff_match_patch.py

@@ -0,0 +1,1919 b''
+#!/usr/bin/python2.4
+
+from __future__ import division
+
+"""Diff Match and Patch
+
+Copyright 2006 Google Inc.
+http://code.google.com/p/google-diff-match-patch/
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+"""
+
+"""Functions for diff, match and patch.
+
+Computes the difference between two texts to create a patch.
+Applies the patch onto another text, allowing for errors.
+"""
+
+__author__ = '[e-mail] (Neil Fraser)'
+
+import math
+import re
+import sys
+import time
+import urllib
+
+class diff_match_patch:
+  """Class containing the diff, match and patch methods.
+
+  Also contains the behaviour settings.
+  """
+
+  def __init__(self):
+    """Inits a diff_match_patch object with default settings.
+    Redefine these in your program to override the defaults.
+    """
+
+    # Number of seconds to map a diff before giving up (0 for infinity).
+    self.Diff_Timeout = 1.0
+    # Cost of an empty edit operation in terms of edit characters.
+    self.Diff_EditCost = 4
+    # At what point is no match declared (0.0 = perfection, 1.0 = very loose).
+    self.Match_Threshold = 0.5
+    # How far to search for a match (0 = exact location, 1000+ = broad match).
+    # A match this many characters away from the expected location will add
+    # 1.0 to the score (0.0 is a perfect match).
+    self.Match_Distance = 1000
+    # When deleting a large block of text (over ~64 characters), how close do
+    # the contents have to be to match the expected contents. (0.0 = perfection,
+    # 1.0 = very loose).  Note that Match_Threshold controls how closely the
+    # end points of a delete need to match.
+    self.Patch_DeleteThreshold = 0.5
+    # Chunk size for context length.
+    self.Patch_Margin = 4
+
+    # The number of bits in an int.
+    # Python has no maximum, thus to disable patch splitting set to 0.
+    # However to avoid long patches in certain pathological cases, use 32.
+    # Multiple short patches (using native ints) are much faster than long ones.
+    self.Match_MaxBits = 32
+
+  #  DIFF FUNCTIONS
+
+  # The data structure representing a diff is an array of tuples:
+  # [(DIFF_DELETE, "Hello"), (DIFF_INSERT, "Goodbye"), (DIFF_EQUAL, " world.")]
+  # which means: delete "Hello", add "Goodbye" and keep " world."
+  DIFF_DELETE = -1
+  DIFF_INSERT = 1
+  DIFF_EQUAL = 0
+
+  def diff_main(self, text1, text2, checklines=True, deadline=None):
+    """Find the differences between two texts.  Simplifies the problem by
+      stripping any common prefix or suffix off the texts before diffing.
+
+    Args:
+      text1: Old string to be diffed.
+      text2: New string to be diffed.
+      checklines: Optional speedup flag.  If present and false, then don't run
+        a line-level diff first to identify the changed areas.
+        Defaults to true, which does a faster, slightly less optimal diff.
+      deadline: Optional time when the diff should be complete by.  Used
+        internally for recursive calls.  Users should set DiffTimeout instead.
+
+    Returns:
+      Array of changes.
+    """
+    # Set a deadline by which time the diff must be complete.
+    if deadline == None:
+      # Unlike in most languages, Python counts time in seconds.
+      if self.Diff_Timeout <= 0:
+        deadline = sys.maxint
+      else:
+        deadline = time.time() + self.Diff_Timeout
+
+    # Check for null inputs.
+    if text1 == None or text2 == None:
+      raise ValueError("Null inputs. (diff_main)")
+
+    # Check for equality (speedup).
+    if text1 == text2:
+      if text1:
+        return [(self.DIFF_EQUAL, text1)]
+      return []
+
+    # Trim off common prefix (speedup).
+    commonlength = self.diff_commonPrefix(text1, text2)
+    commonprefix = text1[:commonlength]
+    text1 = text1[commonlength:]
+    text2 = text2[commonlength:]
+
+    # Trim off common suffix (speedup).
+    commonlength = self.diff_commonSuffix(text1, text2)
+    if commonlength == 0:
+      commonsuffix = ''
+    else:
+      commonsuffix = text1[-commonlength:]
+      text1 = text1[:-commonlength]
+      text2 = text2[:-commonlength]
+
+    # Compute the diff on the middle block.
+    diffs = self.diff_compute(text1, text2, checklines, deadline)
+
+    # Restore the prefix and suffix.
+    if commonprefix:
+      diffs[:0] = [(self.DIFF_EQUAL, commonprefix)]
+    if commonsuffix:
+      diffs.append((self.DIFF_EQUAL, commonsuffix))
+    self.diff_cleanupMerge(diffs)
+    return diffs
+
+  def diff_compute(self, text1, text2, checklines, deadline):
+    """Find the differences between two texts.  Assumes that the texts do not
+      have any common prefix or suffix.
+
+    Args:
+      text1: Old string to be diffed.
+      text2: New string to be diffed.
+      checklines: Speedup flag.  If false, then don't run a line-level diff
+        first to identify the changed areas.
+        If true, then run a faster, slightly less optimal diff.
+      deadline: Time when the diff should be complete by.
+
+    Returns:
+      Array of changes.
+    """
+    if not text1:
+      # Just add some text (speedup).
+      return [(self.DIFF_INSERT, text2)]
+
+    if not text2:
+      # Just delete some text (speedup).
+      return [(self.DIFF_DELETE, text1)]
+
+    if len(text1) > len(text2):
+      (longtext, shorttext) = (text1, text2)
+    else:
+      (shorttext, longtext) = (text1, text2)
+    i = longtext.find(shorttext)
+    if i != -1:
+      # Shorter text is inside the longer text (speedup).
+      diffs = [(self.DIFF_INSERT, longtext[:i]), (self.DIFF_EQUAL, shorttext),
+               (self.DIFF_INSERT, longtext[i + len(shorttext):])]
+      # Swap insertions for deletions if diff is reversed.
+      if len(text1) > len(text2):
+        diffs[0] = (self.DIFF_DELETE, diffs[0][1])
+        diffs[2] = (self.DIFF_DELETE, diffs[2][1])
+      return diffs
+
+    if len(shorttext) == 1:
+      # Single character string.
+      # After the previous speedup, the character can't be an equality.
+      return [(self.DIFF_DELETE, text1), (self.DIFF_INSERT, text2)]
+
+    # Check to see if the problem can be split in two.
+    hm = self.diff_halfMatch(text1, text2)
+    if hm:
+      # A half-match was found, sort out the return data.
+      (text1_a, text1_b, text2_a, text2_b, mid_common) = hm
+      # Send both pairs off for separate processing.
+      diffs_a = self.diff_main(text1_a, text2_a, checklines, deadline)
+      diffs_b = self.diff_main(text1_b, text2_b, checklines, deadline)
+      # Merge the results.
+      return diffs_a + [(self.DIFF_EQUAL, mid_common)] + diffs_b
+
+    if checklines and len(text1) > 100 and len(text2) > 100:
+      return self.diff_lineMode(text1, text2, deadline)
+
+    return self.diff_bisect(text1, text2, deadline)
+
+  def diff_lineMode(self, text1, text2, deadline):
+    """Do a quick line-level diff on both strings, then rediff the parts for
+      greater accuracy.
+      This speedup can produce non-minimal diffs.
+
+    Args:
+      text1: Old string to be diffed.
+      text2: New string to be diffed.
+      deadline: Time when the diff should be complete by.
+
+    Returns:
+      Array of changes.
+    """
+
+    # Scan the text on a line-by-line basis first.
+    (text1, text2, linearray) = self.diff_linesToChars(text1, text2)
+
+    diffs = self.diff_main(text1, text2, False, deadline)
+
+    # Convert the diff back to original text.
+    self.diff_charsToLines(diffs, linearray)
+    # Eliminate freak matches (e.g. blank lines)
+    self.diff_cleanupSemantic(diffs)
+
+    # Rediff any replacement blocks, this time character-by-character.
+    # Add a dummy entry at the end.
+    diffs.append((self.DIFF_EQUAL, ''))
+    pointer = 0
+    count_delete = 0
+    count_insert = 0
+    text_delete = ''
+    text_insert = ''
+    while pointer < len(diffs):
+      if diffs[pointer][0] == self.DIFF_INSERT:
+        count_insert += 1
+        text_insert += diffs[pointer][1]
+      elif diffs[pointer][0] == self.DIFF_DELETE:
+        count_delete += 1
+        text_delete += diffs[pointer][1]
+      elif diffs[pointer][0] == self.DIFF_EQUAL:
+        # Upon reaching an equality, check for prior redundancies.
+        if count_delete >= 1 and count_insert >= 1:
+          # Delete the offending records and add the merged ones.
+          a = self.diff_main(text_delete, text_insert, False, deadline)
+          diffs[pointer - count_delete - count_insert : pointer] = a
+          pointer = pointer - count_delete - count_insert + len(a)
+        count_insert = 0
+        count_delete = 0
+        text_delete = ''
+        text_insert = ''
+
+      pointer += 1
+
+    diffs.pop()  # Remove the dummy entry at the end.
+
+    return diffs
+
+  def diff_bisect(self, text1, text2, deadline):
+    """Find the 'middle snake' of a diff, split the problem in two
+      and return the recursively constructed diff.
+      See Myers 1986 paper: An O(ND) Difference Algorithm and Its Variations.
+
+    Args:
+      text1: Old string to be diffed.
+      text2: New string to be diffed.
+      deadline: Time at which to bail if not yet complete.
+
+    Returns:
+      Array of diff tuples.
+    """
+
+    # Cache the text lengths to prevent multiple calls.
+    text1_length = len(text1)
+    text2_length = len(text2)
+    max_d = (text1_length + text2_length + 1) // 2
+    v_offset = max_d
+    v_length = 2 * max_d
+    v1 = [-1] * v_length
+    v1[v_offset + 1] = 0
+    v2 = v1[:]
+    delta = text1_length - text2_length
+    # If the total number of characters is odd, then the front path will
+    # collide with the reverse path.
+    front = (delta % 2 != 0)
+    # Offsets for start and end of k loop.
+    # Prevents mapping of space beyond the grid.
+    k1start = 0
+    k1end = 0
+    k2start = 0
+    k2end = 0
+    for d in xrange(max_d):
+      # Bail out if deadline is reached.
+      if time.time() > deadline:
+        break
+
+      # Walk the front path one step.
+      for k1 in xrange(-d + k1start, d + 1 - k1end, 2):
+        k1_offset = v_offset + k1
+        if k1 == -d or (k1 != d and
+            v1[k1_offset - 1] < v1[k1_offset + 1]):
+          x1 = v1[k1_offset + 1]
+        else:
+          x1 = v1[k1_offset - 1] + 1
+        y1 = x1 - k1
+        while (x1 < text1_length and y1 < text2_length and
+               text1[x1] == text2[y1]):
+          x1 += 1
+          y1 += 1
+        v1[k1_offset] = x1
+        if x1 > text1_length:
+          # Ran off the right of the graph.
+          k1end += 2
+        elif y1 > text2_length:
+          # Ran off the bottom of the graph.
+          k1start += 2
+        elif front:
+          k2_offset = v_offset + delta - k1
+          if k2_offset >= 0 and k2_offset < v_length and v2[k2_offset] != -1:
+            # Mirror x2 onto top-left coordinate system.
+            x2 = text1_length - v2[k2_offset]
+            if x1 >= x2:
+              # Overlap detected.
+              return self.diff_bisectSplit(text1, text2, x1, y1, deadline)
+
+      # Walk the reverse path one step.
+      for k2 in xrange(-d + k2start, d + 1 - k2end, 2):
+        k2_offset = v_offset + k2
+        if k2 == -d or (k2 != d and
+            v2[k2_offset - 1] < v2[k2_offset + 1]):
+          x2 = v2[k2_offset + 1]
+        else:
+          x2 = v2[k2_offset - 1] + 1
+        y2 = x2 - k2
+        while (x2 < text1_length and y2 < text2_length and
+               text1[-x2 - 1] == text2[-y2 - 1]):
+          x2 += 1
+          y2 += 1
+        v2[k2_offset] = x2
+        if x2 > text1_length:
+          # Ran off the left of the graph.
+          k2end += 2
+        elif y2 > text2_length:
+          # Ran off the top of the graph.
+          k2start += 2
+        elif not front:
+          k1_offset = v_offset + delta - k2
+          if k1_offset >= 0 and k1_offset < v_length and v1[k1_offset] != -1:
+            x1 = v1[k1_offset]
+            y1 = v_offset + x1 - k1_offset
+            # Mirror x2 onto top-left coordinate system.
+            x2 = text1_length - x2
+            if x1 >= x2:
+              # Overlap detected.
+              return self.diff_bisectSplit(text1, text2, x1, y1, deadline)
+
+    # Diff took too long and hit the deadline or
+    # number of diffs equals number of characters, no commonality at all.
+    return [(self.DIFF_DELETE, text1), (self.DIFF_INSERT, text2)]
+
+  def diff_bisectSplit(self, text1, text2, x, y, deadline):
+    """Given the location of the 'middle snake', split the diff in two parts
+    and recurse.
+
+    Args:
+      text1: Old string to be diffed.
+      text2: New string to be diffed.
+      x: Index of split point in text1.
+      y: Index of split point in text2.
+      deadline: Time at which to bail if not yet complete.
+
+    Returns:
+      Array of diff tuples.
+    """
+    text1a = text1[:x]
+    text2a = text2[:y]
+    text1b = text1[x:]
+    text2b = text2[y:]
+
+    # Compute both diffs serially.
+    diffs = self.diff_main(text1a, text2a, False, deadline)
+    diffsb = self.diff_main(text1b, text2b, False, deadline)
+
+    return diffs + diffsb
+
+  def diff_linesToChars(self, text1, text2):
+    """Split two texts into an array of strings.  Reduce the texts to a string
+    of hashes where each Unicode character represents one line.
+
+    Args:
+      text1: First string.
+      text2: Second string.
+
+    Returns:
+      Three element tuple, containing the encoded text1, the encoded text2 and
+      the array of unique strings.  The zeroth element of the array of unique
+      strings is intentionally blank.
+    """
+    lineArray = []  # e.g. lineArray[4] == "Hello\n"
+    lineHash = {}   # e.g. lineHash["Hello\n"] == 4
+
+    # "\x00" is a valid character, but various debuggers don't like it.
+    # So we'll insert a junk entry to avoid generating a null character.
+    lineArray.append('')
+
+    def diff_linesToCharsMunge(text):
+      """Split a text into an array of strings.  Reduce the texts to a string
+      of hashes where each Unicode character represents one line.
+      Modifies linearray and linehash through being a closure.
+
+      Args:
+        text: String to encode.
+
+      Returns:
+        Encoded string.
+      """
+      chars = []
+      # Walk the text, pulling out a substring for each line.
+      # text.split('\n') would would temporarily double our memory footprint.
+      # Modifying text would create many large strings to garbage collect.
+      lineStart = 0
+      lineEnd = -1
+      while lineEnd < len(text) - 1:
+        lineEnd = text.find('\n', lineStart)
+        if lineEnd == -1:
+          lineEnd = len(text) - 1
+        line = text[lineStart:lineEnd + 1]
+        lineStart = lineEnd + 1
+
+        if line in lineHash:
+          chars.append(unichr(lineHash[line]))
+        else:
+          lineArray.append(line)
+          lineHash[line] = len(lineArray) - 1
+          chars.append(unichr(len(lineArray) - 1))
+      return "".join(chars)
+
+    chars1 = diff_linesToCharsMunge(text1)
+    chars2 = diff_linesToCharsMunge(text2)
+    return (chars1, chars2, lineArray)
+
+  def diff_charsToLines(self, diffs, lineArray):
+    """Rehydrate the text in a diff from a string of line hashes to real lines
+    of text.
+
+    Args:
+      diffs: Array of diff tuples.
+      lineArray: Array of unique strings.
+    """
+    for x in xrange(len(diffs)):
+      text = []
+      for char in diffs[x][1]:
+        text.append(lineArray[ord(char)])
+      diffs[x] = (diffs[x][0], "".join(text))
+
+  def diff_commonPrefix(self, text1, text2):
+    """Determine the common prefix of two strings.
+
+    Args:
+      text1: First string.
+      text2: Second string.
+
+    Returns:
+      The number of characters common to the start of each string.
+    """
+    # Quick check for common null cases.
+    if not text1 or not text2 or text1[0] != text2[0]:
+      return 0
+    # Binary search.
+    # Performance analysis: http://neil.fraser.name/news/2007/10/09/
+    pointermin = 0
+    pointermax = min(len(text1), len(text2))
+    pointermid = pointermax
+    pointerstart = 0
+    while pointermin < pointermid:
+      if text1[pointerstart:pointermid] == text2[pointerstart:pointermid]:
+        pointermin = pointermid
+        pointerstart = pointermin
+      else:
+        pointermax = pointermid
+      pointermid = (pointermax - pointermin) // 2 + pointermin
+    return pointermid
+
+  def diff_commonSuffix(self, text1, text2):
+    """Determine the common suffix of two strings.
+
+    Args:
+      text1: First string.
+      text2: Second string.
+
+    Returns:
+      The number of characters common to the end of each string.
+    """
+    # Quick check for common null cases.
+    if not text1 or not text2 or text1[-1] != text2[-1]:
+      return 0
+    # Binary search.
+    # Performance analysis: http://neil.fraser.name/news/2007/10/09/
+    pointermin = 0
+    pointermax = min(len(text1), len(text2))
+    pointermid = pointermax
+    pointerend = 0
+    while pointermin < pointermid:
+      if (text1[-pointermid:len(text1) - pointerend] ==
+          text2[-pointermid:len(text2) - pointerend]):
+        pointermin = pointermid
+        pointerend = pointermin
+      else:
+        pointermax = pointermid
+      pointermid = (pointermax - pointermin) // 2 + pointermin
+    return pointermid
+
+  def diff_commonOverlap(self, text1, text2):
+    """Determine if the suffix of one string is the prefix of another.
+
+    Args:
+      text1 First string.
+      text2 Second string.
+
+    Returns:
+      The number of characters common to the end of the first
+      string and the start of the second string.
+    """
+    # Cache the text lengths to prevent multiple calls.
+    text1_length = len(text1)
+    text2_length = len(text2)
+    # Eliminate the null case.
+    if text1_length == 0 or text2_length == 0:
+      return 0
+    # Truncate the longer string.
+    if text1_length > text2_length:
+      text1 = text1[-text2_length:]
+    elif text1_length < text2_length:
+      text2 = text2[:text1_length]
+    text_length = min(text1_length, text2_length)
+    # Quick check for the worst case.
+    if text1 == text2:
+      return text_length
+
+    # Start by looking for a single character match
+    # and increase length until no match is found.
+    # Performance analysis: http://neil.fraser.name/news/2010/11/04/
+    best = 0
+    length = 1
+    while True:
+      pattern = text1[-length:]
+      found = text2.find(pattern)
+      if found == -1:
+        return best
+      length += found
+      if found == 0 or text1[-length:] == text2[:length]:
+        best = length
+        length += 1
+
+  def diff_halfMatch(self, text1, text2):
+    """Do the two texts share a substring which is at least half the length of
+    the longer text?
+    This speedup can produce non-minimal diffs.
+
+    Args:
+      text1: First string.
+      text2: Second string.
+
+    Returns:
+      Five element Array, containing the prefix of text1, the suffix of text1,
+      the prefix of text2, the suffix of text2 and the common middle.  Or None
+      if there was no match.
+    """
+    if self.Diff_Timeout <= 0:
+      # Don't risk returning a non-optimal diff if we have unlimited time.
+      return None
+    if len(text1) > len(text2):
+      (longtext, shorttext) = (text1, text2)
+    else:
+      (shorttext, longtext) = (text1, text2)
+    if len(longtext) < 4 or len(shorttext) * 2 < len(longtext):
+      return None  # Pointless.
+
+    def diff_halfMatchI(longtext, shorttext, i):
+      """Does a substring of shorttext exist within longtext such that the
+      substring is at least half the length of longtext?
+      Closure, but does not reference any external variables.
+
+      Args:
+        longtext: Longer string.
+        shorttext: Shorter string.
+        i: Start index of quarter length substring within longtext.
+
+      Returns:
+        Five element Array, containing the prefix of longtext, the suffix of
+        longtext, the prefix of shorttext, the suffix of shorttext and the
+        common middle.  Or None if there was no match.
+      """
+      seed = longtext[i:i + len(longtext) // 4]
+      best_common = ''
+      j = shorttext.find(seed)
+      while j != -1:
+        prefixLength = self.diff_commonPrefix(longtext[i:], shorttext[j:])
+        suffixLength = self.diff_commonSuffix(longtext[:i], shorttext[:j])
+        if len(best_common) < suffixLength + prefixLength:
+          best_common = (shorttext[j - suffixLength:j] +
+              shorttext[j:j + prefixLength])
+          best_longtext_a = longtext[:i - suffixLength]
+          best_longtext_b = longtext[i + prefixLength:]
+          best_shorttext_a = shorttext[:j - suffixLength]
+          best_shorttext_b = shorttext[j + prefixLength:]
+        j = shorttext.find(seed, j + 1)
+
+      if len(best_common) * 2 >= len(longtext):
+        return (best_longtext_a, best_longtext_b,
+                best_shorttext_a, best_shorttext_b, best_common)
+      else:
+        return None
+
+    # First check if the second quarter is the seed for a half-match.
+    hm1 = diff_halfMatchI(longtext, shorttext, (len(longtext) + 3) // 4)
+    # Check again based on the third quarter.
+    hm2 = diff_halfMatchI(longtext, shorttext, (len(longtext) + 1) // 2)
+    if not hm1 and not hm2:
+      return None
+    elif not hm2:
+      hm = hm1
+    elif not hm1:
+      hm = hm2
+    else:
+      # Both matched.  Select the longest.
+      if len(hm1[4]) > len(hm2[4]):
+        hm = hm1
+      else:
+        hm = hm2
+
+    # A half-match was found, sort out the return data.
+    if len(text1) > len(text2):
+      (text1_a, text1_b, text2_a, text2_b, mid_common) = hm
+    else:
+      (text2_a, text2_b, text1_a, text1_b, mid_common) = hm
+    return (text1_a, text1_b, text2_a, text2_b, mid_common)
+
+  def diff_cleanupSemantic(self, diffs):
+    """Reduce the number of edits by eliminating semantically trivial
+    equalities.
+
+    Args:
+      diffs: Array of diff tuples.
+    """
+    changes = False
+    equalities = []  # Stack of indices where equalities are found.
+    lastequality = None  # Always equal to diffs[equalities[-1]][1]
+    pointer = 0  # Index of current position.
+    # Number of chars that changed prior to the equality.
+    length_insertions1, length_deletions1 = 0, 0
+    # Number of chars that changed after the equality.
+    length_insertions2, length_deletions2 = 0, 0
+    while pointer < len(diffs):
+      if diffs[pointer][0] == self.DIFF_EQUAL:  # Equality found.
+        equalities.append(pointer)
+        length_insertions1, length_insertions2 = length_insertions2, 0
+        length_deletions1, length_deletions2 = length_deletions2, 0
+        lastequality = diffs[pointer][1]
+      else:  # An insertion or deletion.
+        if diffs[pointer][0] == self.DIFF_INSERT:
+          length_insertions2 += len(diffs[pointer][1])
+        else:
+          length_deletions2 += len(diffs[pointer][1])
+        # Eliminate an equality that is smaller or equal to the edits on both
+        # sides of it.
+        if (lastequality and (len(lastequality) <=
+            max(length_insertions1, length_deletions1)) and
+            (len(lastequality) <= max(length_insertions2, length_deletions2))):
+          # Duplicate record.
+          diffs.insert(equalities[-1], (self.DIFF_DELETE, lastequality))
+          # Change second copy to insert.
+          diffs[equalities[-1] + 1] = (self.DIFF_INSERT,
+              diffs[equalities[-1] + 1][1])
+          # Throw away the equality we just deleted.
+          equalities.pop()
+          # Throw away the previous equality (it needs to be reevaluated).
+          if len(equalities):
+            equalities.pop()
+          if len(equalities):
+            pointer = equalities[-1]
+          else:
+            pointer = -1
+          # Reset the counters.
+          length_insertions1, length_deletions1 = 0, 0
+          length_insertions2, length_deletions2 = 0, 0
+          lastequality = None
+          changes = True
+      pointer += 1
+
+    # Normalize the diff.
+    if changes:
+      self.diff_cleanupMerge(diffs)
+    self.diff_cleanupSemanticLossless(diffs)
+
+    # Find any overlaps between deletions and insertions.
+    # e.g: <del>abcxxx</del><ins>xxxdef</ins>
+    #   -> <del>abc</del>xxx<ins>def</ins>
+    # e.g: <del>xxxabc</del><ins>defxxx</ins>
+    #   -> <ins>def</ins>xxx<del>abc</del>
+    # Only extract an overlap if it is as big as the edit ahead or behind it.
+    pointer = 1
+    while pointer < len(diffs):
+      if (diffs[pointer - 1][0] == self.DIFF_DELETE and
+          diffs[pointer][0] == self.DIFF_INSERT):
+        deletion = diffs[pointer - 1][1]
+        insertion = diffs[pointer][1]
+        overlap_length1 = self.diff_commonOverlap(deletion, insertion)
+        overlap_length2 = self.diff_commonOverlap(insertion, deletion)
+        if overlap_length1 >= overlap_length2:
+          if (overlap_length1 >= len(deletion) / 2.0 or
+              overlap_length1 >= len(insertion) / 2.0):
+            # Overlap found.  Insert an equality and trim the surrounding edits.
+            diffs.insert(pointer, (self.DIFF_EQUAL,
+                                   insertion[:overlap_length1]))
+            diffs[pointer - 1] = (self.DIFF_DELETE,
+                                  deletion[:len(deletion) - overlap_length1])
+            diffs[pointer + 1] = (self.DIFF_INSERT,
+                                  insertion[overlap_length1:])
+            pointer += 1
+        else:
+          if (overlap_length2 >= len(deletion) / 2.0 or
+              overlap_length2 >= len(insertion) / 2.0):
+            # Reverse overlap found.
+            # Insert an equality and swap and trim the surrounding edits.
+            diffs.insert(pointer, (self.DIFF_EQUAL, deletion[:overlap_length2]))
+            diffs[pointer - 1] = (self.DIFF_INSERT,
+                                  insertion[:len(insertion) - overlap_length2])
+            diffs[pointer + 1] = (self.DIFF_DELETE, deletion[overlap_length2:])
+            pointer += 1
+        pointer += 1
+      pointer += 1
+
+  def diff_cleanupSemanticLossless(self, diffs):
+    """Look for single edits surrounded on both sides by equalities
+    which can be shifted sideways to align the edit to a word boundary.
+    e.g: The c<ins>at c</ins>ame. -> The <ins>cat </ins>came.
+
+    Args:
+      diffs: Array of diff tuples.
+    """
+
+    def diff_cleanupSemanticScore(one, two):
+      """Given two strings, compute a score representing whether the
+      internal boundary falls on logical boundaries.
+      Scores range from 6 (best) to 0 (worst).
+      Closure, but does not reference any external variables.
+
+      Args:
+        one: First string.
+        two: Second string.
+
+      Returns:
+        The score.
+      """
+      if not one or not two:
+        # Edges are the best.
+        return 6
+
+      # Each port of this function behaves slightly differently due to
+      # subtle differences in each language's definition of things like
+      # 'whitespace'.  Since this function's purpose is largely cosmetic,
+      # the choice has been made to use each language's native features
+      # rather than force total conformity.
+      char1 = one[-1]
+      char2 = two[0]
+      nonAlphaNumeric1 = not char1.isalnum()
+      nonAlphaNumeric2 = not char2.isalnum()
+      whitespace1 = nonAlphaNumeric1 and char1.isspace()
+      whitespace2 = nonAlphaNumeric2 and char2.isspace()
+      lineBreak1 = whitespace1 and (char1 == "\r" or char1 == "\n")
+      lineBreak2 = whitespace2 and (char2 == "\r" or char2 == "\n")
+      blankLine1 = lineBreak1 and self.BLANKLINEEND.search(one)
+      blankLine2 = lineBreak2 and self.BLANKLINESTART.match(two)
+
+      if blankLine1 or blankLine2:
+        # Five points for blank lines.
+        return 5
+      elif lineBreak1 or lineBreak2:
+        # Four points for line breaks.
+        return 4
+      elif nonAlphaNumeric1 and not whitespace1 and whitespace2:
+        # Three points for end of sentences.
+        return 3
+      elif whitespace1 or whitespace2:
+        # Two points for whitespace.
+        return 2
+      elif nonAlphaNumeric1 or nonAlphaNumeric2:
+        # One point for non-alphanumeric.
+        return 1
+      return 0
+
+    pointer = 1
+    # Intentionally ignore the first and last element (don't need checking).
+    while pointer < len(diffs) - 1:
+      if (diffs[pointer - 1][0] == self.DIFF_EQUAL and
+          diffs[pointer + 1][0] == self.DIFF_EQUAL):
+        # This is a single edit surrounded by equalities.
+        equality1 = diffs[pointer - 1][1]
+        edit = diffs[pointer][1]
+        equality2 = diffs[pointer + 1][1]
+
+        # First, shift the edit as far left as possible.
+        commonOffset = self.diff_commonSuffix(equality1, edit)
+        if commonOffset:
+          commonString = edit[-commonOffset:]
+          equality1 = equality1[:-commonOffset]
+          edit = commonString + edit[:-commonOffset]
+          equality2 = commonString + equality2
+
+        # Second, step character by character right, looking for the best fit.
+        bestEquality1 = equality1
+        bestEdit = edit
+        bestEquality2 = equality2
+        bestScore = (diff_cleanupSemanticScore(equality1, edit) +
+            diff_cleanupSemanticScore(edit, equality2))
+        while edit and equality2 and edit[0] == equality2[0]:
+          equality1 += edit[0]
+          edit = edit[1:] + equality2[0]
+          equality2 = equality2[1:]
+          score = (diff_cleanupSemanticScore(equality1, edit) +
+              diff_cleanupSemanticScore(edit, equality2))
+          # The >= encourages trailing rather than leading whitespace on edits.
+          if score >= bestScore:
+            bestScore = score
+            bestEquality1 = equality1
+            bestEdit = edit
+            bestEquality2 = equality2
+
+        if diffs[pointer - 1][1] != bestEquality1:
+          # We have an improvement, save it back to the diff.
+          if bestEquality1:
+            diffs[pointer - 1] = (diffs[pointer - 1][0], bestEquality1)
+          else:
+            del diffs[pointer - 1]
+            pointer -= 1
+          diffs[pointer] = (diffs[pointer][0], bestEdit)
+          if bestEquality2:
+            diffs[pointer + 1] = (diffs[pointer + 1][0], bestEquality2)
+          else:
+            del diffs[pointer + 1]
+            pointer -= 1
+      pointer += 1
+
+  # Define some regex patterns for matching boundaries.
+  BLANKLINEEND = re.compile(r"\n\r?\n$");
+  BLANKLINESTART = re.compile(r"^\r?\n\r?\n");
+
+  def diff_cleanupEfficiency(self, diffs):
+    """Reduce the number of edits by eliminating operationally trivial
+    equalities.
+
+    Args:
+      diffs: Array of diff tuples.
+    """
+    changes = False
+    equalities = []  # Stack of indices where equalities are found.
+    lastequality = None  # Always equal to diffs[equalities[-1]][1]
+    pointer = 0  # Index of current position.
+    pre_ins = False  # Is there an insertion operation before the last equality.
+    pre_del = False  # Is there a deletion operation before the last equality.
+    post_ins = False  # Is there an insertion operation after the last equality.
+    post_del = False  # Is there a deletion operation after the last equality.
+    while pointer < len(diffs):
+      if diffs[pointer][0] == self.DIFF_EQUAL:  # Equality found.
+        if (len(diffs[pointer][1]) < self.Diff_EditCost and
+            (post_ins or post_del)):
+          # Candidate found.
+          equalities.append(pointer)
+          pre_ins = post_ins
+          pre_del = post_del
+          lastequality = diffs[pointer][1]
+        else:
+          # Not a candidate, and can never become one.
+          equalities = []
+          lastequality = None
+
+        post_ins = post_del = False
+      else:  # An insertion or deletion.
+        if diffs[pointer][0] == self.DIFF_DELETE:
+          post_del = True
+        else:
+          post_ins = True
+
+        # Five types to be split:
+        # <ins>A</ins><del>B</del>XY<ins>C</ins><del>D</del>
+        # <ins>A</ins>X<ins>C</ins><del>D</del>
+        # <ins>A</ins><del>B</del>X<ins>C</ins>
+        # <ins>A</del>X<ins>C</ins><del>D</del>
+        # <ins>A</ins><del>B</del>X<del>C</del>
+
+        if lastequality and ((pre_ins and pre_del and post_ins and post_del) or
+                             ((len(lastequality) < self.Diff_EditCost / 2) and
+                              (pre_ins + pre_del + post_ins + post_del) == 3)):
+          # Duplicate record.
+          diffs.insert(equalities[-1], (self.DIFF_DELETE, lastequality))
+          # Change second copy to insert.
+          diffs[equalities[-1] + 1] = (self.DIFF_INSERT,
+              diffs[equalities[-1] + 1][1])
+          equalities.pop()  # Throw away the equality we just deleted.
+          lastequality = None
+          if pre_ins and pre_del:
+            # No changes made which could affect previous entry, keep going.
+            post_ins = post_del = True
+            equalities = []
+          else:
+            if len(equalities):
+              equalities.pop()  # Throw away the previous equality.
+            if len(equalities):
+              pointer = equalities[-1]
+            else:
+              pointer = -1
+            post_ins = post_del = False
+          changes = True
+      pointer += 1
+
+    if changes:
+      self.diff_cleanupMerge(diffs)
+
+  def diff_cleanupMerge(self, diffs):
+    """Reorder and merge like edit sections.  Merge equalities.
+    Any edit section can move as long as it doesn't cross an equality.
+
+    Args:
+      diffs: Array of diff tuples.
+    """
+    diffs.append((self.DIFF_EQUAL, ''))  # Add a dummy entry at the end.
+    pointer = 0
+    count_delete = 0
+    count_insert = 0
+    text_delete = ''
+    text_insert = ''
+    while pointer < len(diffs):
+      if diffs[pointer][0] == self.DIFF_INSERT:
+        count_insert += 1
+        text_insert += diffs[pointer][1]
+        pointer += 1
+      elif diffs[pointer][0] == self.DIFF_DELETE:
+        count_delete += 1
+        text_delete += diffs[pointer][1]
+        pointer += 1
+      elif diffs[pointer][0] == self.DIFF_EQUAL:
+        # Upon reaching an equality, check for prior redundancies.
+        if count_delete + count_insert > 1:
+          if count_delete != 0 and count_insert != 0:
+            # Factor out any common prefixies.
+            commonlength = self.diff_commonPrefix(text_insert, text_delete)
+            if commonlength != 0:
+              x = pointer - count_delete - count_insert - 1
+              if x >= 0 and diffs[x][0] == self.DIFF_EQUAL:
+                diffs[x] = (diffs[x][0], diffs[x][1] +
+                            text_insert[:commonlength])
+              else:
+                diffs.insert(0, (self.DIFF_EQUAL, text_insert[:commonlength]))
+                pointer += 1
+              text_insert = text_insert[commonlength:]
+              text_delete = text_delete[commonlength:]
+            # Factor out any common suffixies.
+            commonlength = self.diff_commonSuffix(text_insert, text_delete)
+            if commonlength != 0:
+              diffs[pointer] = (diffs[pointer][0], text_insert[-commonlength:] +
+                  diffs[pointer][1])
+              text_insert = text_insert[:-commonlength]
+              text_delete = text_delete[:-commonlength]
+          # Delete the offending records and add the merged ones.
+          if count_delete == 0:
+            diffs[pointer - count_insert : pointer] = [
+                (self.DIFF_INSERT, text_insert)]
+          elif count_insert == 0:
+            diffs[pointer - count_delete : pointer] = [
+                (self.DIFF_DELETE, text_delete)]
+          else:
+            diffs[pointer - count_delete - count_insert : pointer] = [
+                (self.DIFF_DELETE, text_delete),
+                (self.DIFF_INSERT, text_insert)]
+          pointer = pointer - count_delete - count_insert + 1
+          if count_delete != 0:
+            pointer += 1
+          if count_insert != 0:
+            pointer += 1
+        elif pointer != 0 and diffs[pointer - 1][0] == self.DIFF_EQUAL:
+          # Merge this equality with the previous one.
+          diffs[pointer - 1] = (diffs[pointer - 1][0],
+                                diffs[pointer - 1][1] + diffs[pointer][1])
+          del diffs[pointer]
+        else:
+          pointer += 1
+
+        count_insert = 0
+        count_delete = 0
+        text_delete = ''
+        text_insert = ''
+
+    if diffs[-1][1] == '':
+      diffs.pop()  # Remove the dummy entry at the end.
+
+    # Second pass: look for single edits surrounded on both sides by equalities
+    # which can be shifted sideways to eliminate an equality.
+    # e.g: A<ins>BA</ins>C -> <ins>AB</ins>AC
+    changes = False
+    pointer = 1
+    # Intentionally ignore the first and last element (don't need checking).
+    while pointer < len(diffs) - 1:
+      if (diffs[pointer - 1][0] == self.DIFF_EQUAL and
+          diffs[pointer + 1][0] == self.DIFF_EQUAL):
+        # This is a single edit surrounded by equalities.
+        if diffs[pointer][1].endswith(diffs[pointer - 1][1]):
+          # Shift the edit over the previous equality.
+          diffs[pointer] = (diffs[pointer][0],
+              diffs[pointer - 1][1] +
+              diffs[pointer][1][:-len(diffs[pointer - 1][1])])
+          diffs[pointer + 1] = (diffs[pointer + 1][0],
+                                diffs[pointer - 1][1] + diffs[pointer + 1][1])
+          del diffs[pointer - 1]
+          changes = True
+        elif diffs[pointer][1].startswith(diffs[pointer + 1][1]):
+          # Shift the edit over the next equality.
+          diffs[pointer - 1] = (diffs[pointer - 1][0],
+                                diffs[pointer - 1][1] + diffs[pointer + 1][1])
+          diffs[pointer] = (diffs[pointer][0],
+              diffs[pointer][1][len(diffs[pointer + 1][1]):] +
+              diffs[pointer + 1][1])
+          del diffs[pointer + 1]
+          changes = True
+      pointer += 1
+
+    # If shifts were made, the diff needs reordering and another shift sweep.
+    if changes:
+      self.diff_cleanupMerge(diffs)
+
+  def diff_xIndex(self, diffs, loc):
+    """loc is a location in text1, compute and return the equivalent location
+    in text2.  e.g. "The cat" vs "The big cat", 1->1, 5->8
+
+    Args:
+      diffs: Array of diff tuples.
+      loc: Location within text1.
+
+    Returns:
+      Location within text2.
+    """
+    chars1 = 0
+    chars2 = 0
+    last_chars1 = 0
+    last_chars2 = 0
+    for x in xrange(len(diffs)):
+      (op, text) = diffs[x]
+      if op != self.DIFF_INSERT:  # Equality or deletion.
+        chars1 += len(text)
+      if op != self.DIFF_DELETE:  # Equality or insertion.
+        chars2 += len(text)
+      if chars1 > loc:  # Overshot the location.
+        break
+      last_chars1 = chars1
+      last_chars2 = chars2
+
+    if len(diffs) != x and diffs[x][0] == self.DIFF_DELETE:
+      # The location was deleted.
+      return last_chars2
+    # Add the remaining len(character).
+    return last_chars2 + (loc - last_chars1)
+
+  def diff_prettyHtml(self, diffs):
+    """Convert a diff array into a pretty HTML report.
+
+    Args:
+      diffs: Array of diff tuples.
+
+    Returns:
+      HTML representation.
+    """
+    html = []
+    for (op, data) in diffs:
+      text = (data.replace("&", "&amp;").replace("<", "&lt;")
+                 .replace(">", "&gt;").replace("\n", "&para;<br>"))
+      if op == self.DIFF_INSERT:
+        html.append("<ins style=\"background:#e6ffe6;\">%s</ins>" % text)
+      elif op == self.DIFF_DELETE:
+        html.append("<del style=\"background:#ffe6e6;\">%s</del>" % text)
+      elif op == self.DIFF_EQUAL:
+        html.append("<span>%s</span>" % text)
+    return "".join(html)
+
+  def diff_text1(self, diffs):
+    """Compute and return the source text (all equalities and deletions).
+
+    Args:
+      diffs: Array of diff tuples.
+
+    Returns:
+      Source text.
+    """
+    text = []
+    for (op, data) in diffs:
+      if op != self.DIFF_INSERT:
+        text.append(data)
+    return "".join(text)
+
+  def diff_text2(self, diffs):
+    """Compute and return the destination text (all equalities and insertions).
+
+    Args:
+      diffs: Array of diff tuples.
+
+    Returns:
+      Destination text.
+    """
+    text = []
+    for (op, data) in diffs:
+      if op != self.DIFF_DELETE:
+        text.append(data)
+    return "".join(text)
+
+  def diff_levenshtein(self, diffs):
+    """Compute the Levenshtein distance; the number of inserted, deleted or
+    substituted characters.
+
+    Args:
+      diffs: Array of diff tuples.
+
+    Returns:
+      Number of changes.
+    """
+    levenshtein = 0
+    insertions = 0
+    deletions = 0
+    for (op, data) in diffs:
+      if op == self.DIFF_INSERT:
+        insertions += len(data)
+      elif op == self.DIFF_DELETE:
+        deletions += len(data)
+      elif op == self.DIFF_EQUAL:
+        # A deletion and an insertion is one substitution.
+        levenshtein += max(insertions, deletions)
+        insertions = 0
+        deletions = 0
+    levenshtein += max(insertions, deletions)
+    return levenshtein
+
+  def diff_toDelta(self, diffs):
+    """Crush the diff into an encoded string which describes the operations
+    required to transform text1 into text2.
+    E.g. =3\t-2\t+ing  -> Keep 3 chars, delete 2 chars, insert 'ing'.
+    Operations are tab-separated.  Inserted text is escaped using %xx notation.
+
+    Args:
+      diffs: Array of diff tuples.
+
+    Returns:
+      Delta text.
+    """
+    text = []
+    for (op, data) in diffs:
+      if op == self.DIFF_INSERT:
+        # High ascii will raise UnicodeDecodeError.  Use Unicode instead.
+        data = data.encode("utf-8")
+        text.append("+" + urllib.quote(data, "!~*'();/?:@&=+$,# "))
+      elif op == self.DIFF_DELETE:
+        text.append("-%d" % len(data))
+      elif op == self.DIFF_EQUAL:
+        text.append("=%d" % len(data))
+    return "\t".join(text)
+
+  def diff_fromDelta(self, text1, delta):
+    """Given the original text1, and an encoded string which describes the
+    operations required to transform text1 into text2, compute the full diff.
+
+    Args:
+      text1: Source string for the diff.
+      delta: Delta text.
+
+    Returns:
+      Array of diff tuples.
+
+    Raises:
+      ValueError: If invalid input.
+    """
+    if type(delta) == unicode:
+      # Deltas should be composed of a subset of ascii chars, Unicode not
+      # required.  If this encode raises UnicodeEncodeError, delta is invalid.
+      delta = delta.encode("ascii")
+    diffs = []
+    pointer = 0  # Cursor in text1
+    tokens = delta.split("\t")
+    for token in tokens:
+      if token == "":
+        # Blank tokens are ok (from a trailing \t).
+        continue
+      # Each token begins with a one character parameter which specifies the
+      # operation of this token (delete, insert, equality).
+      param = token[1:]
+      if token[0] == "+":
+        param = urllib.unquote(param).decode("utf-8")
+        diffs.append((self.DIFF_INSERT, param))
+      elif token[0] == "-" or token[0] == "=":
+        try:
+          n = int(param)
+        except ValueError:
+          raise ValueError("Invalid number in diff_fromDelta: " + param)
+        if n < 0:
+          raise ValueError("Negative number in diff_fromDelta: " + param)
+        text = text1[pointer : pointer + n]
+        pointer += n
+        if token[0] == "=":
+          diffs.append((self.DIFF_EQUAL, text))
+        else:
+          diffs.append((self.DIFF_DELETE, text))
+      else:
+        # Anything else is an error.
+        raise ValueError("Invalid diff operation in diff_fromDelta: " +
+            token[0])
+    if pointer != len(text1):
+      raise ValueError(
+          "Delta length (%d) does not equal source text length (%d)." %
+         (pointer, len(text1)))
+    return diffs
+
+  #  MATCH FUNCTIONS
+
+  def match_main(self, text, pattern, loc):
+    """Locate the best instance of 'pattern' in 'text' near 'loc'.
+
+    Args:
+      text: The text to search.
+      pattern: The pattern to search for.
+      loc: The location to search around.
+
+    Returns:
+      Best match index or -1.
+    """
+    # Check for null inputs.
+    if text == None or pattern == None:
+      raise ValueError("Null inputs. (match_main)")
+
+    loc = max(0, min(loc, len(text)))
+    if text == pattern:
+      # Shortcut (potentially not guaranteed by the algorithm)
+      return 0
+    elif not text:
+      # Nothing to match.
+      return -1
+    elif text[loc:loc + len(pattern)] == pattern:
+      # Perfect match at the perfect spot!  (Includes case of null pattern)
+      return loc
+    else:
+      # Do a fuzzy compare.
+      match = self.match_bitap(text, pattern, loc)
+      return match
+
+  def match_bitap(self, text, pattern, loc):
+    """Locate the best instance of 'pattern' in 'text' near 'loc' using the
+    Bitap algorithm.
+
+    Args:
+      text: The text to search.
+      pattern: The pattern to search for.
+      loc: The location to search around.
+
+    Returns:
+      Best match index or -1.
+    """
+    # Python doesn't have a maxint limit, so ignore this check.
+    #if self.Match_MaxBits != 0 and len(pattern) > self.Match_MaxBits:
+    #  raise ValueError("Pattern too long for this application.")
+
+    # Initialise the alphabet.
+    s = self.match_alphabet(pattern)
+
+    def match_bitapScore(e, x):
+      """Compute and return the score for a match with e errors and x location.
+      Accesses loc and pattern through being a closure.
+
+      Args:
+        e: Number of errors in match.
+        x: Location of match.
+
+      Returns:
+        Overall score for match (0.0 = good, 1.0 = bad).
+      """
+      accuracy = float(e) / len(pattern)
+      proximity = abs(loc - x)
+      if not self.Match_Distance:
+        # Dodge divide by zero error.
+        return proximity and 1.0 or accuracy
+      return accuracy + (proximity / float(self.Match_Distance))
+
+    # Highest score beyond which we give up.
+    score_threshold = self.Match_Threshold
+    # Is there a nearby exact match? (speedup)
+    best_loc = text.find(pattern, loc)
+    if best_loc != -1:
+      score_threshold = min(match_bitapScore(0, best_loc), score_threshold)
+      # What about in the other direction? (speedup)
+      best_loc = text.rfind(pattern, loc + len(pattern))
+      if best_loc != -1:
+        score_threshold = min(match_bitapScore(0, best_loc), score_threshold)
+
+    # Initialise the bit arrays.
+    matchmask = 1 << (len(pattern) - 1)
+    best_loc = -1
+
+    bin_max = len(pattern) + len(text)
+    # Empty initialization added to appease pychecker.
+    last_rd = None
+    for d in xrange(len(pattern)):
+      # Scan for the best match each iteration allows for one more error.
+      # Run a binary search to determine how far from 'loc' we can stray at
+      # this error level.
+      bin_min = 0
+      bin_mid = bin_max
+      while bin_min < bin_mid:
+        if match_bitapScore(d, loc + bin_mid) <= score_threshold:
+          bin_min = bin_mid
+        else:
+          bin_max = bin_mid
+        bin_mid = (bin_max - bin_min) // 2 + bin_min
+
+      # Use the result from this iteration as the maximum for the next.
+      bin_max = bin_mid
+      start = max(1, loc - bin_mid + 1)
+      finish = min(loc + bin_mid, len(text)) + len(pattern)
+
+      rd = [0] * (finish + 2)
+      rd[finish + 1] = (1 << d) - 1
+      for j in xrange(finish, start - 1, -1):
+        if len(text) <= j - 1:
+          # Out of range.
+          charMatch = 0
+        else:
+          charMatch = s.get(text[j - 1], 0)
+        if d == 0:  # First pass: exact match.
+          rd[j] = ((rd[j + 1] << 1) | 1) & charMatch
+        else:  # Subsequent passes: fuzzy match.
+          rd[j] = (((rd[j + 1] << 1) | 1) & charMatch) | (
+              ((last_rd[j + 1] | last_rd[j]) << 1) | 1) | last_rd[j + 1]
+        if rd[j] & matchmask:
+          score = match_bitapScore(d, j - 1)
+          # This match will almost certainly be better than any existing match.
+          # But check anyway.
+          if score <= score_threshold:
+            # Told you so.
+            score_threshold = score
+            best_loc = j - 1
+            if best_loc > loc:
+              # When passing loc, don't exceed our current distance from loc.
+              start = max(1, 2 * loc - best_loc)
+            else:
+              # Already passed loc, downhill from here on in.
+              break
+      # No hope for a (better) match at greater error levels.
+      if match_bitapScore(d + 1, loc) > score_threshold:
+        break
+      last_rd = rd
+    return best_loc
+
+  def match_alphabet(self, pattern):
+    """Initialise the alphabet for the Bitap algorithm.
+
+    Args:
+      pattern: The text to encode.
+
+    Returns:
+      Hash of character locations.
+    """
+    s = {}
+    for char in pattern:
+      s[char] = 0
+    for i in xrange(len(pattern)):
+      s[pattern[i]] |= 1 << (len(pattern) - i - 1)
+    return s
+
+  #  PATCH FUNCTIONS
+
+  def patch_addContext(self, patch, text):
+    """Increase the context until it is unique,
+    but don't let the pattern expand beyond Match_MaxBits.
+
+    Args:
+      patch: The patch to grow.
+      text: Source text.
+    """
+    if len(text) == 0:
+      return
+    pattern = text[patch.start2 : patch.start2 + patch.length1]
+    padding = 0
+
+    # Look for the first and last matches of pattern in text.  If two different
+    # matches are found, increase the pattern length.
+    while (text.find(pattern) != text.rfind(pattern) and (self.Match_MaxBits ==
+        0 or len(pattern) < self.Match_MaxBits - self.Patch_Margin -
+        self.Patch_Margin)):
+      padding += self.Patch_Margin
+      pattern = text[max(0, patch.start2 - padding) :
+                     patch.start2 + patch.length1 + padding]
+    # Add one chunk for good luck.
+    padding += self.Patch_Margin
+
+    # Add the prefix.
+    prefix = text[max(0, patch.start2 - padding) : patch.start2]
+    if prefix:
+      patch.diffs[:0] = [(self.DIFF_EQUAL, prefix)]
+    # Add the suffix.
+    suffix = text[patch.start2 + patch.length1 :
+                  patch.start2 + patch.length1 + padding]
+    if suffix:
+      patch.diffs.append((self.DIFF_EQUAL, suffix))
+
+    # Roll back the start points.
+    patch.start1 -= len(prefix)
+    patch.start2 -= len(prefix)
+    # Extend lengths.
+    patch.length1 += len(prefix) + len(suffix)
+    patch.length2 += len(prefix) + len(suffix)
+
+  def patch_make(self, a, b=None, c=None):
+    """Compute a list of patches to turn text1 into text2.
+    Use diffs if provided, otherwise compute it ourselves.
+    There are four ways to call this function, depending on what data is
+    available to the caller:
+    Method 1:
+    a = text1, b = text2
+    Method 2:
+    a = diffs
+    Method 3 (optimal):
+    a = text1, b = diffs
+    Method 4 (deprecated, use method 3):
+    a = text1, b = text2, c = diffs
+
+    Args:
+      a: text1 (methods 1,3,4) or Array of diff tuples for text1 to
+          text2 (method 2).
+      b: text2 (methods 1,4) or Array of diff tuples for text1 to
+          text2 (method 3) or undefined (method 2).
+      c: Array of diff tuples for text1 to text2 (method 4) or
+          undefined (methods 1,2,3).
+
+    Returns:
+      Array of Patch objects.
+    """
+    text1 = None
+    diffs = None
+    # Note that texts may arrive as 'str' or 'unicode'.
+    if isinstance(a, basestring) and isinstance(b, basestring) and c is None:
+      # Method 1: text1, text2
+      # Compute diffs from text1 and text2.
+      text1 = a
+      diffs = self.diff_main(text1, b, True)
+      if len(diffs) > 2:
+        self.diff_cleanupSemantic(diffs)
+        self.diff_cleanupEfficiency(diffs)
+    elif isinstance(a, list) and b is None and c is None:
+      # Method 2: diffs
+      # Compute text1 from diffs.
+      diffs = a
+      text1 = self.diff_text1(diffs)
+    elif isinstance(a, basestring) and isinstance(b, list) and c is None:
+      # Method 3: text1, diffs
+      text1 = a
+      diffs = b
+    elif (isinstance(a, basestring) and isinstance(b, basestring) and
+          isinstance(c, list)):
+      # Method 4: text1, text2, diffs
+      # text2 is not used.
+      text1 = a
+      diffs = c
+    else:
+      raise ValueError("Unknown call format to patch_make.")
+
+    if not diffs:
+      return []  # Get rid of the None case.
+    patches = []
+    patch = patch_obj()
+    char_count1 = 0  # Number of characters into the text1 string.
+    char_count2 = 0  # Number of characters into the text2 string.
+    prepatch_text = text1  # Recreate the patches to determine context info.
+    postpatch_text = text1
+    for x in xrange(len(diffs)):
+      (diff_type, diff_text) = diffs[x]
+      if len(patch.diffs) == 0 and diff_type != self.DIFF_EQUAL:
+        # A new patch starts here.
+        patch.start1 = char_count1
+        patch.start2 = char_count2
+      if diff_type == self.DIFF_INSERT:
+        # Insertion
+        patch.diffs.append(diffs[x])
+        patch.length2 += len(diff_text)
+        postpatch_text = (postpatch_text[:char_count2] + diff_text +
+                          postpatch_text[char_count2:])
+      elif diff_type == self.DIFF_DELETE:
+        # Deletion.
+        patch.length1 += len(diff_text)
+        patch.diffs.append(diffs[x])
+        postpatch_text = (postpatch_text[:char_count2] +
+                          postpatch_text[char_count2 + len(diff_text):])
+      elif (diff_type == self.DIFF_EQUAL and
+            len(diff_text) <= 2 * self.Patch_Margin and
+            len(patch.diffs) != 0 and len(diffs) != x + 1):
+        # Small equality inside a patch.
+        patch.diffs.append(diffs[x])
+        patch.length1 += len(diff_text)
+        patch.length2 += len(diff_text)
+
+      if (diff_type == self.DIFF_EQUAL and
+          len(diff_text) >= 2 * self.Patch_Margin):
+        # Time for a new patch.
+        if len(patch.diffs) != 0:
+          self.patch_addContext(patch, prepatch_text)
+          patches.append(patch)
+          patch = patch_obj()
+          # Unlike Unidiff, our patch lists have a rolling context.
+          # http://code.google.com/p/google-diff-match-patch/wiki/Unidiff
+          # Update prepatch text & pos to reflect the application of the
+          # just completed patch.
+          prepatch_text = postpatch_text
+          char_count1 = char_count2
+
+      # Update the current character count.
+      if diff_type != self.DIFF_INSERT:
+        char_count1 += len(diff_text)
+      if diff_type != self.DIFF_DELETE:
+        char_count2 += len(diff_text)
+
+    # Pick up the leftover patch if not empty.
+    if len(patch.diffs) != 0:
+      self.patch_addContext(patch, prepatch_text)
+      patches.append(patch)
+    return patches
+
+  def patch_deepCopy(self, patches):
+    """Given an array of patches, return another array that is identical.
+
+    Args:
+      patches: Array of Patch objects.
+
+    Returns:
+      Array of Patch objects.
+    """
+    patchesCopy = []
+    for patch in patches:
+      patchCopy = patch_obj()
+      # No need to deep copy the tuples since they are immutable.
+      patchCopy.diffs = patch.diffs[:]
+      patchCopy.start1 = patch.start1
+      patchCopy.start2 = patch.start2
+      patchCopy.length1 = patch.length1
+      patchCopy.length2 = patch.length2
+      patchesCopy.append(patchCopy)
+    return patchesCopy
+
+  def patch_apply(self, patches, text):
+    """Merge a set of patches onto the text.  Return a patched text, as well
+    as a list of true/false values indicating which patches were applied.
+
+    Args:
+      patches: Array of Patch objects.
+      text: Old text.
+
+    Returns:
+      Two element Array, containing the new text and an array of boolean values.
+    """
+    if not patches:
+      return (text, [])
+
+    # Deep copy the patches so that no changes are made to originals.
+    patches = self.patch_deepCopy(patches)
+
+    nullPadding = self.patch_addPadding(patches)
+    text = nullPadding + text + nullPadding
+    self.patch_splitMax(patches)
+
+    # delta keeps track of the offset between the expected and actual location
+    # of the previous patch.  If there are patches expected at positions 10 and
+    # 20, but the first patch was found at 12, delta is 2 and the second patch
+    # has an effective expected position of 22.
+    delta = 0
+    results = []
+    for patch in patches:
+      expected_loc = patch.start2 + delta
+      text1 = self.diff_text1(patch.diffs)
+      end_loc = -1
+      if len(text1) > self.Match_MaxBits:
+        # patch_splitMax will only provide an oversized pattern in the case of
+        # a monster delete.
+        start_loc = self.match_main(text, text1[:self.Match_MaxBits],
+                                    expected_loc)
+        if start_loc != -1:
+          end_loc = self.match_main(text, text1[-self.Match_MaxBits:],
+              expected_loc + len(text1) - self.Match_MaxBits)
+          if end_loc == -1 or start_loc >= end_loc:
+            # Can't find valid trailing context.  Drop this patch.
+            start_loc = -1
+      else:
+        start_loc = self.match_main(text, text1, expected_loc)
+      if start_loc == -1:
+        # No match found.  :(
+        results.append(False)
+        # Subtract the delta for this failed patch from subsequent patches.
+        delta -= patch.length2 - patch.length1
+      else:
+        # Found a match.  :)
+        results.append(True)
+        delta = start_loc - expected_loc
+        if end_loc == -1:
+          text2 = text[start_loc : start_loc + len(text1)]
+        else:
+          text2 = text[start_loc : end_loc + self.Match_MaxBits]
+        if text1 == text2:
+          # Perfect match, just shove the replacement text in.
+          text = (text[:start_loc] + self.diff_text2(patch.diffs) +
+                      text[start_loc + len(text1):])
+        else:
+          # Imperfect match.
+          # Run a diff to get a framework of equivalent indices.
+          diffs = self.diff_main(text1, text2, False)
+          if (len(text1) > self.Match_MaxBits and
+              self.diff_levenshtein(diffs) / float(len(text1)) >
+              self.Patch_DeleteThreshold):
+            # The end points match, but the content is unacceptably bad.
+            results[-1] = False
+          else:
+            self.diff_cleanupSemanticLossless(diffs)
+            index1 = 0
+            for (op, data) in patch.diffs:
+              if op != self.DIFF_EQUAL:
+                index2 = self.diff_xIndex(diffs, index1)
+              if op == self.DIFF_INSERT:  # Insertion
+                text = text[:start_loc + index2] + data + text[start_loc +
+                                                               index2:]
+              elif op == self.DIFF_DELETE:  # Deletion
+                text = text[:start_loc + index2] + text[start_loc +
+                    self.diff_xIndex(diffs, index1 + len(data)):]
+              if op != self.DIFF_DELETE:
+                index1 += len(data)
+    # Strip the padding off.
+    text = text[len(nullPadding):-len(nullPadding)]
+    return (text, results)
+
+  def patch_addPadding(self, patches):
+    """Add some padding on text start and end so that edges can match
+    something.  Intended to be called only from within patch_apply.
+
+    Args:
+      patches: Array of Patch objects.
+
+    Returns:
+      The padding string added to each side.
+    """
+    paddingLength = self.Patch_Margin
+    nullPadding = ""
+    for x in xrange(1, paddingLength + 1):
+      nullPadding += chr(x)
+
+    # Bump all the patches forward.
+    for patch in patches:
+      patch.start1 += paddingLength
+      patch.start2 += paddingLength
+
+    # Add some padding on start of first diff.
+    patch = patches[0]
+    diffs = patch.diffs
+    if not diffs or diffs[0][0] != self.DIFF_EQUAL:
+      # Add nullPadding equality.
+      diffs.insert(0, (self.DIFF_EQUAL, nullPadding))
+      patch.start1 -= paddingLength  # Should be 0.
+      patch.start2 -= paddingLength  # Should be 0.
+      patch.length1 += paddingLength
+      patch.length2 += paddingLength
+    elif paddingLength > len(diffs[0][1]):
+      # Grow first equality.
+      extraLength = paddingLength - len(diffs[0][1])
+      newText = nullPadding[len(diffs[0][1]):] + diffs[0][1]
+      diffs[0] = (diffs[0][0], newText)
+      patch.start1 -= extraLength
+      patch.start2 -= extraLength
+      patch.length1 += extraLength
+      patch.length2 += extraLength
+
+    # Add some padding on end of last diff.
+    patch = patches[-1]
+    diffs = patch.diffs
+    if not diffs or diffs[-1][0] != self.DIFF_EQUAL:
+      # Add nullPadding equality.
+      diffs.append((self.DIFF_EQUAL, nullPadding))
+      patch.length1 += paddingLength
+      patch.length2 += paddingLength
+    elif paddingLength > len(diffs[-1][1]):
+      # Grow last equality.
+      extraLength = paddingLength - len(diffs[-1][1])
+      newText = diffs[-1][1] + nullPadding[:extraLength]
+      diffs[-1] = (diffs[-1][0], newText)
+      patch.length1 += extraLength
+      patch.length2 += extraLength
+
+    return nullPadding
+
+  def patch_splitMax(self, patches):
+    """Look through the patches and break up any which are longer than the
+    maximum limit of the match algorithm.
+    Intended to be called only from within patch_apply.
+
+    Args:
+      patches: Array of Patch objects.
+    """
+    patch_size = self.Match_MaxBits
+    if patch_size == 0:
+      # Python has the option of not splitting strings due to its ability
+      # to handle integers of arbitrary precision.
+      return
+    for x in xrange(len(patches)):
+      if patches[x].length1 <= patch_size:
+        continue
+      bigpatch = patches[x]
+      # Remove the big old patch.
+      del patches[x]
+      x -= 1
+      start1 = bigpatch.start1
+      start2 = bigpatch.start2
+      precontext = ''
+      while len(bigpatch.diffs) != 0:
+        # Create one of several smaller patches.
+        patch = patch_obj()
+        empty = True
+        patch.start1 = start1 - len(precontext)
+        patch.start2 = start2 - len(precontext)
+        if precontext:
+          patch.length1 = patch.length2 = len(precontext)
+          patch.diffs.append((self.DIFF_EQUAL, precontext))
+
+        while (len(bigpatch.diffs) != 0 and
+               patch.length1 < patch_size - self.Patch_Margin):
+          (diff_type, diff_text) = bigpatch.diffs[0]
+          if diff_type == self.DIFF_INSERT:
+            # Insertions are harmless.
+            patch.length2 += len(diff_text)
+            start2 += len(diff_text)
+            patch.diffs.append(bigpatch.diffs.pop(0))
+            empty = False
+          elif (diff_type == self.DIFF_DELETE and len(patch.diffs) == 1 and
+              patch.diffs[0][0] == self.DIFF_EQUAL and
+              len(diff_text) > 2 * patch_size):
+            # This is a large deletion.  Let it pass in one chunk.
+            patch.length1 += len(diff_text)
+            start1 += len(diff_text)
+            empty = False
+            patch.diffs.append((diff_type, diff_text))
+            del bigpatch.diffs[0]
+          else:
+            # Deletion or equality.  Only take as much as we can stomach.
+            diff_text = diff_text[:patch_size - patch.length1 -
+                                  self.Patch_Margin]
+            patch.length1 += len(diff_text)
+            start1 += len(diff_text)
+            if diff_type == self.DIFF_EQUAL:
+              patch.length2 += len(diff_text)
+              start2 += len(diff_text)
+            else:
+              empty = False
+
+            patch.diffs.append((diff_type, diff_text))
+            if diff_text == bigpatch.diffs[0][1]:
+              del bigpatch.diffs[0]
+            else:
+              bigpatch.diffs[0] = (bigpatch.diffs[0][0],
+                                   bigpatch.diffs[0][1][len(diff_text):])
+
+        # Compute the head context for the next patch.
+        precontext = self.diff_text2(patch.diffs)
+        precontext = precontext[-self.Patch_Margin:]
+        # Append the end context for this patch.
+        postcontext = self.diff_text1(bigpatch.diffs)[:self.Patch_Margin]
+        if postcontext:
+          patch.length1 += len(postcontext)
+          patch.length2 += len(postcontext)
+          if len(patch.diffs) != 0 and patch.diffs[-1][0] == self.DIFF_EQUAL:
+            patch.diffs[-1] = (self.DIFF_EQUAL, patch.diffs[-1][1] +
+                               postcontext)
+          else:
+            patch.diffs.append((self.DIFF_EQUAL, postcontext))
+
+        if not empty:
+          x += 1
+          patches.insert(x, patch)
+
+  def patch_toText(self, patches):
+    """Take a list of patches and return a textual representation.
+
+    Args:
+      patches: Array of Patch objects.
+
+    Returns:
+      Text representation of patches.
+    """
+    text = []
+    for patch in patches:
+      text.append(str(patch))
+    return "".join(text)
+
+  def patch_fromText(self, textline):
+    """Parse a textual representation of patches and return a list of patch
+    objects.
+
+    Args:
+      textline: Text representation of patches.
+
+    Returns:
+      Array of Patch objects.
+
+    Raises:
+      ValueError: If invalid input.
+    """
+    if type(textline) == unicode:
+      # Patches should be composed of a subset of ascii chars, Unicode not
+      # required.  If this encode raises UnicodeEncodeError, patch is invalid.
+      textline = textline.encode("ascii")
+    patches = []
+    if not textline:
+      return patches
+    text = textline.split('\n')
+    while len(text) != 0:
+      m = re.match("^@@ -(\d+),?(\d*) \+(\d+),?(\d*) @@$", text[0])
+      if not m:
+        raise ValueError("Invalid patch string: " + text[0])
+      patch = patch_obj()
+      patches.append(patch)
+      patch.start1 = int(m.group(1))
+      if m.group(2) == '':
+        patch.start1 -= 1
+        patch.length1 = 1
+      elif m.group(2) == '0':
+        patch.length1 = 0
+      else:
+        patch.start1 -= 1
+        patch.length1 = int(m.group(2))
+
+      patch.start2 = int(m.group(3))
+      if m.group(4) == '':
+        patch.start2 -= 1
+        patch.length2 = 1
+      elif m.group(4) == '0':
+        patch.length2 = 0
+      else:
+        patch.start2 -= 1
+        patch.length2 = int(m.group(4))
+
+      del text[0]
+
+      while len(text) != 0:
+        if text[0]:
+          sign = text[0][0]
+        else:
+          sign = ''
+        line = urllib.unquote(text[0][1:])
+        line = line.decode("utf-8")
+        if sign == '+':
+          # Insertion.
+          patch.diffs.append((self.DIFF_INSERT, line))
+        elif sign == '-':
+          # Deletion.
+          patch.diffs.append((self.DIFF_DELETE, line))
+        elif sign == ' ':
+          # Minor equality.
+          patch.diffs.append((self.DIFF_EQUAL, line))
+        elif sign == '@':
+          # Start of next patch.
+          break
+        elif sign == '':
+          # Blank line?  Whatever.
+          pass
+        else:
+          # WTF?
+          raise ValueError("Invalid patch mode: '%s'\n%s" % (sign, line))
+        del text[0]
+    return patches
+
+
+class patch_obj:
+  """Class representing one patch operation.
+  """
+
+  def __init__(self):
+    """Initializes with an empty list of diffs.
+    """
+    self.diffs = []
+    self.start1 = None
+    self.start2 = None
+    self.length1 = 0
+    self.length2 = 0
+
+  def __str__(self):
+    """Emmulate GNU diff's format.
+    Header: @@ -382,8 +481,9 @@
+    Indicies are printed as 1-based, not 0-based.
+
+    Returns:
+      The GNU diff string.
+    """
+    if self.length1 == 0:
+      coords1 = str(self.start1) + ",0"
+    elif self.length1 == 1:
+      coords1 = str(self.start1 + 1)
+    else:
+      coords1 = str(self.start1 + 1) + "," + str(self.length1)
+    if self.length2 == 0:
+      coords2 = str(self.start2) + ",0"
+    elif self.length2 == 1:
+      coords2 = str(self.start2 + 1)
+    else:
+      coords2 = str(self.start2 + 1) + "," + str(self.length2)
+    text = ["@@ -", coords1, " +", coords2, " @@\n"]
+    # Escape the body of the patch with %xx notation.
+    for (op, data) in self.diffs:
+      if op == diff_match_patch.DIFF_INSERT:
+        text.append("+")
+      elif op == diff_match_patch.DIFF_DELETE:
+        text.append("-")
+      elif op == diff_match_patch.DIFF_EQUAL:
+        text.append(" ")
+      # High ascii will raise UnicodeDecodeError.  Use Unicode instead.
+      data = data.encode("utf-8")
+      text.append(urllib.quote(data, "!~*'();/?:@&=+$,# ") + "\n")
+    return "".join(text)
  No newline at end of file

rhodecode/templates/codeblocks/diffs.html

@@ -0,0 +1,398 b''
+<%def name="diff_line_anchor(filename, line, type)"><%
+return '%s_%s_%i' % (h.safeid(filename), type, line)
+%></%def>
+
+<%def name="action_class(action)"><%
+    return {
+        '-': 'cb-deletion',
+        '+': 'cb-addition',
+        ' ': 'cb-context',
+        }.get(action, 'cb-empty')
+%></%def>
+
+<%def name="op_class(op_id)"><%
+    return {
+        DEL_FILENODE: 'deletion', # file deleted
+        BIN_FILENODE: 'warning' # binary diff hidden
+    }.get(op_id, 'addition')
+%></%def>
+
+<%def name="link_for(**kw)"><%
+new_args = request.GET.mixed()
+new_args.update(kw)
+return h.url('', **new_args)
+%></%def>
+
+<%def name="render_diffset(diffset,
+
+    # collapse all file diff entries when there are more than this amount of files in the diff
+    collapse_when_files_over=20,
+
+    # collapse lines in the diff when more than this amount of lines changed in the file diff
+    lines_changed_limit=500,
+)">
+<%
+# TODO: dan: move this to an argument - and set a cookie so that it is saved
+# default option for future requests
+diff_mode = request.GET.get('diffmode', 'sideside')
+if diff_mode not in ('sideside', 'unified'):
+    diff_mode = 'sideside'
+
+collapse_all = len(diffset.files) > collapse_when_files_over
+%>
+
+%if diff_mode == 'sideside':
+<style>
+.wrapper {
+    max-width: 1600px !important;
+}
+</style>
+%endif
+
+% if diffset.limited_diff:
+<div class="alert alert-warning">
+    ${_('The requested commit is too big and content was truncated.')} <a href="${link_for(fulldiff=1)}" onclick="return confirm('${_("Showing a big diff might take some time and resources, continue?")}')">${_('Show full diff')}</a>
+</div>
+% endif
+
+<div class="cs_files">
+    <div class="cs_files_title">
+        %if diffset.files:
+        <div class="pull-right">
+            <div class="btn-group">
+                <a
+                    class="btn ${diff_mode == 'sideside' and 'btn-primary'} tooltip"
+                    title="${_('View side by side')}"
+                    href="${link_for(diffmode='sideside')}">
+                    <span>${_('Side by Side')}</span>
+                </a>
+                <a
+                    class="btn ${diff_mode == 'unified' and 'btn-primary'} tooltip"
+                    title="${_('View unified')}" href="${link_for(diffmode='unified')}">
+                    <span>${_('Unified')}</span>
+                </a>
+            </div>
+        </div>
+        <div class="pull-left">
+            <div class="btn-group">
+                <a
+                    class="btn"
+                    href="#"
+                    onclick="$('input[class=diff-collapse-state]').prop('checked', false); return false">${_('Expand All')}</a>
+                <a
+                    class="btn"
+                    href="#"
+                    onclick="$('input[class=diff-collapse-state]').prop('checked', true); return false">${_('Collapse All')}</a>
+            </div>
+        </div>
+        %endif
+        <h2 style="padding: 5px; text-align: center;">
+    %if diffset.limited_diff:
+        ${ungettext('%(num)s file changed', '%(num)s files changed', diffset.changed_files) % {'num': diffset.changed_files}}
+    %else:
+        ${ungettext('%(num)s file changed: %(linesadd)s inserted, ''%(linesdel)s deleted',
+                    '%(num)s files changed: %(linesadd)s inserted, %(linesdel)s deleted', diffset.changed_files) % {'num': diffset.changed_files, 'linesadd': diffset.lines_added, 'linesdel': diffset.lines_deleted}}
+    %endif
+        </h2>
+    </div>
+
+    %if not diffset.files:
+        <p class="empty_data">${_('No files')}</p>
+    %endif
+
+    <div class="filediffs">
+    %for i, filediff in enumerate(diffset.files):
+    <%
+    lines_changed = filediff['patch']['stats']['added'] + filediff['patch']['stats']['deleted']
+    over_lines_changed_limit = lines_changed > lines_changed_limit
+    %>
+        <input ${collapse_all and 'checked' or ''} class="diff-collapse-state" id="diff-collapse-${i}" type="checkbox">
+        <div
+            class="diff"
+            data-f-path="${filediff['patch']['filename']}"
+            id="a_${h.FID('', filediff['patch']['filename'])}">
+            <label for="diff-collapse-${i}" class="diff-heading">
+                <div class="diff-collapse-indicator"></div>
+                ${diff_ops(filediff)}
+            </label>
+            ${diff_menu(filediff)}
+            <table class="cb cb-diff-${diff_mode} code-highlight ${over_lines_changed_limit and 'cb-collapsed' or ''}">
+        %if not filediff.hunks:
+            %for op_id, op_text in filediff['patch']['stats']['ops'].items():
+                <tr>
+                    <td class="cb-text cb-${op_class(op_id)}" ${diff_mode == 'unified' and 'colspan=3' or 'colspan=4'}>
+                        %if op_id == DEL_FILENODE:
+                        ${_('File was deleted')}
+                        %elif op_id == BIN_FILENODE:
+                        ${_('Binary file hidden')}
+                        %else:
+                        ${op_text}
+                        %endif
+                    </td>
+                </tr>
+            %endfor
+        %endif
+        %if over_lines_changed_limit:
+                <tr class="cb-warning cb-collapser">
+                    <td class="cb-text" ${diff_mode == 'unified' and 'colspan=3' or 'colspan=4'}>
+                        ${_('This diff has been collapsed as it changes many lines, (%i lines changed)' % lines_changed)}
+                        <a href="#" class="cb-expand"
+                           onclick="$(this).closest('table').removeClass('cb-collapsed'); return false;">${_('Show them')}
+                        </a>
+                        <a href="#" class="cb-collapse"
+                           onclick="$(this).closest('table').addClass('cb-collapsed'); return false;">${_('Hide them')}
+                        </a>
+                    </td>
+                </tr>
+        %endif
+        %if filediff.patch['is_limited_diff']:
+                <tr class="cb-warning cb-collapser">
+                    <td class="cb-text" ${diff_mode == 'unified' and 'colspan=3' or 'colspan=4'}>
+                        ${_('The requested commit is too big and content was truncated.')} <a href="${link_for(fulldiff=1)}" onclick="return confirm('${_("Showing a big diff might take some time and resources, continue?")}')">${_('Show full diff')}</a>
+                    </td>
+                </tr>
+        %endif
+        %for hunk in filediff.hunks:
+                <tr class="cb-hunk">
+                    <td ${diff_mode == 'unified' and 'colspan=2' or ''}>
+                        ## TODO: dan: add ajax loading of more context here
+                        ## <a href="#">
+                            <i class="icon-more"></i>
+                        ## </a>
+                    </td>
+                    <td ${diff_mode == 'sideside' and 'colspan=3' or ''}>
+                        @@
+                        -${hunk.source_start},${hunk.source_length}
+                        +${hunk.target_start},${hunk.target_length}
+                        ${hunk.section_header}
+                    </td>
+                </tr>
+            %if diff_mode == 'unified':
+                    ${render_hunk_lines_unified(hunk)}
+            %elif diff_mode == 'sideside':
+                    ${render_hunk_lines_sideside(hunk)}
+            %else:
+                <tr class="cb-line">
+                    <td>unknown diff mode</td>
+                </tr>
+            %endif
+        %endfor
+            </table>
+        </div>
+    %endfor
+    </div>
+</div>
+</%def>
+
+<%def name="diff_ops(filediff)">
+<%
+stats = filediff['patch']['stats']
+from rhodecode.lib.diffs import NEW_FILENODE, DEL_FILENODE, \
+    MOD_FILENODE, RENAMED_FILENODE, CHMOD_FILENODE, BIN_FILENODE
+%>
+    <span class="diff-pill">
+        %if filediff.source_file_path and filediff.target_file_path:
+            %if filediff.source_file_path != filediff.target_file_path: # file was renamed
+                  <strong>${filediff.target_file_path}</strong> ⬅ <del>${filediff.source_file_path}</del>
+            %else:
+                ## file was modified
+                <strong>${filediff.source_file_path}</strong>
+            %endif
+        %else:
+            %if filediff.source_file_path:
+                ## file was deleted
+                <strong>${filediff.source_file_path}</strong>
+            %else:
+                ## file was added
+                <strong>${filediff.target_file_path}</strong>
+            %endif
+        %endif
+    </span>
+    <span class="diff-pill-group" style="float: left">
+        %if filediff.patch['is_limited_diff']:
+        <span class="diff-pill tooltip" op="limited" title="The stats for this diff are not complete">limited diff</span>
+        %endif
+        %if RENAMED_FILENODE in stats['ops']:
+        <span class="diff-pill" op="renamed">renamed</span>
+        %endif
+
+        %if NEW_FILENODE in stats['ops']:
+        <span class="diff-pill" op="created">created</span>
+            %if filediff['target_mode'].startswith('120'):
+        <span class="diff-pill" op="symlink">symlink</span>
+            %else:
+        <span class="diff-pill" op="mode">${nice_mode(filediff['target_mode'])}</span>
+            %endif
+        %endif
+
+        %if DEL_FILENODE in stats['ops']:
+        <span class="diff-pill" op="removed">removed</span>
+        %endif
+
+        %if CHMOD_FILENODE in stats['ops']:
+        <span class="diff-pill" op="mode">
+            ${nice_mode(filediff['source_mode'])} ➡ ${nice_mode(filediff['target_mode'])}
+        </span>
+        %endif
+    </span>
+
+    <a class="diff-pill diff-anchor" href="#a_${h.FID('', filediff.patch['filename'])}">¶</a>
+
+    <span class="diff-pill-group" style="float: right">
+        %if BIN_FILENODE in stats['ops']:
+        <span class="diff-pill" op="binary">binary</span>
+            %if MOD_FILENODE in stats['ops']:
+            <span class="diff-pill" op="modified">modified</span>
+            %endif
+        %endif
+        %if stats['deleted']:
+        <span class="diff-pill" op="deleted">-${stats['deleted']}</span>
+        %endif
+        %if stats['added']:
+        <span class="diff-pill" op="added">+${stats['added']}</span>
+        %endif
+    </span>
+
+</%def>
+
+<%def name="nice_mode(filemode)">
+    ${filemode.startswith('100') and filemode[3:] or filemode}
+</%def>
+
+<%def name="diff_menu(filediff)">
+    <div class="diff-menu">
+%if filediff.diffset.source_ref:
+    %if filediff.patch['operation'] in ['D', 'M']:
+        <a
+            class="tooltip"
+            href="${h.url('files_home',repo_name=c.repo_name,f_path=filediff.source_file_path,revision=filediff.diffset.source_ref)}"
+            title="${h.tooltip(_('Show file at commit: %(commit_id)s') % {'commit_id': filediff.diffset.source_ref[:12]})}"
+        >
+            ${_('Show file before')}
+        </a>
+    %else:
+        <a
+            disabled
+            class="tooltip"
+            title="${h.tooltip(_('File no longer present at commit: %(commit_id)s') % {'commit_id': filediff.diffset.source_ref[:12]})}"
+        >
+            ${_('Show file before')}
+        </a>
+    %endif
+    %if filediff.patch['operation'] in ['A', 'M']:
+        <a
+            class="tooltip"
+            href="${h.url('files_home',repo_name=c.repo_name,f_path=filediff.target_file_path,revision=filediff.diffset.target_ref)}"
+            title="${h.tooltip(_('Show file at commit: %(commit_id)s') % {'commit_id': filediff.diffset.target_ref[:12]})}"
+        >
+            ${_('Show file after')}
+        </a>
+    %else:
+        <a
+            disabled
+            class="tooltip"
+            title="${h.tooltip(_('File no longer present at commit: %(commit_id)s') % {'commit_id': filediff.diffset.target_ref[:12]})}"
+            >
+                ${_('Show file after')}
+        </a>
+    %endif
+        <a
+            class="tooltip"
+            title="${h.tooltip(_('Raw diff'))}"
+            href="${h.url('files_diff_home',repo_name=c.repo_name,f_path=filediff.target_file_path,diff2=filediff.diffset.target_ref,diff1=filediff.diffset.source_ref,diff='raw')}"
+        >
+            ${_('Raw diff')}
+        </a>
+        <a
+            class="tooltip"
+            title="${h.tooltip(_('Download diff'))}"
+            href="${h.url('files_diff_home',repo_name=c.repo_name,f_path=filediff.target_file_path,diff2=filediff.diffset.target_ref,diff1=filediff.diffset.source_ref,diff='download')}"
+        >
+            ${_('Download diff')}
+        </a>
+%endif
+    </div>
+</%def>
+
+
+<%def name="render_hunk_lines_sideside(hunk)">
+    %for i, line in enumerate(hunk.sideside):
+    <%
+    old_line_anchor, new_line_anchor = None, None
+    if line.original.lineno:
+        old_line_anchor = diff_line_anchor(hunk.filediff.source_file_path, line.original.lineno, 'o')
+    if line.modified.lineno:
+        new_line_anchor = diff_line_anchor(hunk.filediff.target_file_path, line.modified.lineno, 'n')
+    %>
+    <tr class="cb-line">
+        <td class="cb-lineno ${action_class(line.original.action)}"
+            data-line-number="${line.original.lineno}"
+            %if old_line_anchor:
+            id="${old_line_anchor}"
+            %endif
+        >
+            %if line.original.lineno:
+            <a name="${old_line_anchor}" href="#${old_line_anchor}">${line.original.lineno}</a>
+            %endif
+        </td>
+        <td class="cb-content ${action_class(line.original.action)}"
+            data-line-number="o${line.original.lineno}"
+            ><span class="cb-code">${line.original.action} ${line.original.content or '' | n}</span>
+        </td>
+        <td class="cb-lineno ${action_class(line.modified.action)}"
+            data-line-number="${line.modified.lineno}"
+            %if new_line_anchor:
+            id="${new_line_anchor}"
+            %endif
+            >
+            %if line.modified.lineno:
+                <a name="${new_line_anchor}" href="#${new_line_anchor}">${line.modified.lineno}</a>
+            %endif
+            </td>
+        <td class="cb-content ${action_class(line.modified.action)}"
+            data-line-number="n${line.modified.lineno}"
+            >
+            <span class="cb-code">${line.modified.action} ${line.modified.content or '' | n}</span>
+        </td>
+    </tr>
+    %endfor
+</%def>
+
+
+<%def name="render_hunk_lines_unified(hunk)">
+    %for old_line_no, new_line_no, action, content in hunk.unified:
+    <%
+    old_line_anchor, new_line_anchor = None, None
+    if old_line_no:
+        old_line_anchor = diff_line_anchor(hunk.filediff.source_file_path, old_line_no, 'o')
+    if new_line_no:
+        new_line_anchor = diff_line_anchor(hunk.filediff.target_file_path, new_line_no, 'n')
+    %>
+    <tr class="cb-line">
+        <td class="cb-lineno ${action_class(action)}"
+            data-line-number="${old_line_no}"
+            %if old_line_anchor:
+            id="${old_line_anchor}"
+            %endif
+        >
+            %if old_line_anchor:
+            <a name="${old_line_anchor}" href="#${old_line_anchor}">${old_line_no}</a>
+            %endif
+        </td>
+        <td class="cb-lineno ${action_class(action)}"
+            data-line-number="${new_line_no}"
+            %if new_line_anchor:
+            id="${new_line_anchor}"
+            %endif
+        >
+            %if new_line_anchor:
+            <a name="${new_line_anchor}" href="#${new_line_anchor}">${new_line_no}</a>
+            %endif
+        </td>
+        <td class="cb-content ${action_class(action)}"
+            data-line-number="${new_line_no and 'n' or 'o'}${new_line_no or old_line_no}"
+            ><span class="cb-code">${action} ${content or '' | n}</span>
+          </td>
+    </tr>
+    %endfor
+</%def>

LICENSE.txt

@@ -1,694 +1,696 b''
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU Affero General Public License, version 3
 (only), as published by the Free Software Foundation.
 
 
 This program incorporates work covered by the following copyright and
 permission notice:
 
    Copyright (c) 2014-2016 - packaging
        file:
    Copyright (c) 2008-2011 - msgpack-python
        file:licenses/msgpack_license.txt
    Copyright (c) 2009 - tornado
        file:licenses/tornado_license.txt
    Copyright (c) 2015 - pygments-markdown-lexer
        file:licenses/pygments_markdown_lexer_license.txt
+   Copyright 2006 - diff_match_patch
+       file:licenses/diff_match_patch_license.txt
 
 All licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
 You may obtain a copy of the License at
 
     http://www.apache.org/licenses/LICENSE-2.0
 
 Unless required by applicable law or agreed to in writing, software
 distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 imitations under the License.
 
 
 Below is the full text of GNU Affero General Public License, version 3
 
 
                     GNU AFFERO GENERAL PUBLIC LICENSE
                        Version 3, 19 November 2007
 
  Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
  Everyone is permitted to copy and distribute verbatim copies
  of this license document, but changing it is not allowed.
 
                             Preamble
 
   The GNU Affero General Public License is a free, copyleft license for
 software and other kinds of works, specifically designed to ensure
 cooperation with the community in the case of network server software.
 
   The licenses for most software and other practical works are designed
 to take away your freedom to share and change the works.  By contrast,
 our General Public Licenses are intended to guarantee your freedom to
 share and change all versions of a program--to make sure it remains free
 software for all its users.
 
   When we speak of free software, we are referring to freedom, not
 price.  Our General Public Licenses are designed to make sure that you
 have the freedom to distribute copies of free software (and charge for
 them if you wish), that you receive source code or can get it if you
 want it, that you can change the software or use pieces of it in new
 free programs, and that you know you can do these things.
 
   Developers that use our General Public Licenses protect your rights
 with two steps: (1) assert copyright on the software, and (2) offer
 you this License which gives you legal permission to copy, distribute
 and/or modify the software.
 
   A secondary benefit of defending all users' freedom is that
 improvements made in alternate versions of the program, if they
 receive widespread use, become available for other developers to
 incorporate.  Many developers of free software are heartened and
 encouraged by the resulting cooperation.  However, in the case of
 software used on network servers, this result may fail to come about.
 The GNU General Public License permits making a modified version and
 letting the public access it on a server without ever releasing its
 source code to the public.
 
   The GNU Affero General Public License is designed specifically to
 ensure that, in such cases, the modified source code becomes available
 to the community.  It requires the operator of a network server to
 provide the source code of the modified version running there to the
 users of that server.  Therefore, public use of a modified version, on
 a publicly accessible server, gives the public access to the source
 code of the modified version.
 
   An older license, called the Affero General Public License and
 published by Affero, was designed to accomplish similar goals.  This is
 a different license, not a version of the Affero GPL, but Affero has
 released a new version of the Affero GPL which permits relicensing under
 this license.
 
   The precise terms and conditions for copying, distribution and
 modification follow.
 
                        TERMS AND CONDITIONS
 
   0. Definitions.
 
   "This License" refers to version 3 of the GNU Affero General Public License.
 
   "Copyright" also means copyright-like laws that apply to other kinds of
 works, such as semiconductor masks.
 
   "The Program" refers to any copyrightable work licensed under this
 License.  Each licensee is addressed as "you".  "Licensees" and
 "recipients" may be individuals or organizations.
 
   To "modify" a work means to copy from or adapt all or part of the work
 in a fashion requiring copyright permission, other than the making of an
 exact copy.  The resulting work is called a "modified version" of the
 earlier work or a work "based on" the earlier work.
 
   A "covered work" means either the unmodified Program or a work based
 on the Program.
 
   To "propagate" a work means to do anything with it that, without
 permission, would make you directly or secondarily liable for
 infringement under applicable copyright law, except executing it on a
 computer or modifying a private copy.  Propagation includes copying,
 distribution (with or without modification), making available to the
 public, and in some countries other activities as well.
 
   To "convey" a work means any kind of propagation that enables other
 parties to make or receive copies.  Mere interaction with a user through
 a computer network, with no transfer of a copy, is not conveying.
 
   An interactive user interface displays "Appropriate Legal Notices"
 to the extent that it includes a convenient and prominently visible
 feature that (1) displays an appropriate copyright notice, and (2)
 tells the user that there is no warranty for the work (except to the
 extent that warranties are provided), that licensees may convey the
 work under this License, and how to view a copy of this License.  If
 the interface presents a list of user commands or options, such as a
 menu, a prominent item in the list meets this criterion.
 
   1. Source Code.
 
   The "source code" for a work means the preferred form of the work
 for making modifications to it.  "Object code" means any non-source
 form of a work.
 
   A "Standard Interface" means an interface that either is an official
 standard defined by a recognized standards body, or, in the case of
 interfaces specified for a particular programming language, one that
 is widely used among developers working in that language.
 
   The "System Libraries" of an executable work include anything, other
 than the work as a whole, that (a) is included in the normal form of
 packaging a Major Component, but which is not part of that Major
 Component, and (b) serves only to enable use of the work with that
 Major Component, or to implement a Standard Interface for which an
 implementation is available to the public in source code form.  A
 "Major Component", in this context, means a major essential component
 (kernel, window system, and so on) of the specific operating system
 (if any) on which the executable work runs, or a compiler used to
 produce the work, or an object code interpreter used to run it.
 
   The "Corresponding Source" for a work in object code form means all
 the source code needed to generate, install, and (for an executable
 work) run the object code and to modify the work, including scripts to
 control those activities.  However, it does not include the work's
 System Libraries, or general-purpose tools or generally available free
 programs which are used unmodified in performing those activities but
 which are not part of the work.  For example, Corresponding Source
 includes interface definition files associated with source files for
 the work, and the source code for shared libraries and dynamically
 linked subprograms that the work is specifically designed to require,
 such as by intimate data communication or control flow between those
 subprograms and other parts of the work.
 
   The Corresponding Source need not include anything that users
 can regenerate automatically from other parts of the Corresponding
 Source.
 
   The Corresponding Source for a work in source code form is that
 same work.
 
   2. Basic Permissions.
 
   All rights granted under this License are granted for the term of
 copyright on the Program, and are irrevocable provided the stated
 conditions are met.  This License explicitly affirms your unlimited
 permission to run the unmodified Program.  The output from running a
 covered work is covered by this License only if the output, given its
 content, constitutes a covered work.  This License acknowledges your
 rights of fair use or other equivalent, as provided by copyright law.
 
   You may make, run and propagate covered works that you do not
 convey, without conditions so long as your license otherwise remains
 in force.  You may convey covered works to others for the sole purpose
 of having them make modifications exclusively for you, or provide you
 with facilities for running those works, provided that you comply with
 the terms of this License in conveying all material for which you do
 not control copyright.  Those thus making or running the covered works
 for you must do so exclusively on your behalf, under your direction
 and control, on terms that prohibit them from making any copies of
 your copyrighted material outside their relationship with you.
 
   Conveying under any other circumstances is permitted solely under
 the conditions stated below.  Sublicensing is not allowed; section 10
 makes it unnecessary.
 
   3. Protecting Users' Legal Rights From Anti-Circumvention Law.
 
   No covered work shall be deemed part of an effective technological
 measure under any applicable law fulfilling obligations under article
 11 of the WIPO copyright treaty adopted on 20 December 1996, or
 similar laws prohibiting or restricting circumvention of such
 measures.
 
   When you convey a covered work, you waive any legal power to forbid
 circumvention of technological measures to the extent such circumvention
 is effected by exercising rights under this License with respect to
 the covered work, and you disclaim any intention to limit operation or
 modification of the work as a means of enforcing, against the work's
 users, your or third parties' legal rights to forbid circumvention of
 technological measures.
 
   4. Conveying Verbatim Copies.
 
   You may convey verbatim copies of the Program's source code as you
 receive it, in any medium, provided that you conspicuously and
 appropriately publish on each copy an appropriate copyright notice;
 keep intact all notices stating that this License and any
 non-permissive terms added in accord with section 7 apply to the code;
 keep intact all notices of the absence of any warranty; and give all
 recipients a copy of this License along with the Program.
 
   You may charge any price or no price for each copy that you convey,
 and you may offer support or warranty protection for a fee.
 
   5. Conveying Modified Source Versions.
 
   You may convey a work based on the Program, or the modifications to
 produce it from the Program, in the form of source code under the
 terms of section 4, provided that you also meet all of these conditions:
 
     a) The work must carry prominent notices stating that you modified
     it, and giving a relevant date.
 
     b) The work must carry prominent notices stating that it is
     released under this License and any conditions added under section
     7.  This requirement modifies the requirement in section 4 to
     "keep intact all notices".
 
     c) You must license the entire work, as a whole, under this
     License to anyone who comes into possession of a copy.  This
     License will therefore apply, along with any applicable section 7
     additional terms, to the whole of the work, and all its parts,
     regardless of how they are packaged.  This License gives no
     permission to license the work in any other way, but it does not
     invalidate such permission if you have separately received it.
 
     d) If the work has interactive user interfaces, each must display
     Appropriate Legal Notices; however, if the Program has interactive
     interfaces that do not display Appropriate Legal Notices, your
     work need not make them do so.
 
   A compilation of a covered work with other separate and independent
 works, which are not by their nature extensions of the covered work,
 and which are not combined with it such as to form a larger program,
 in or on a volume of a storage or distribution medium, is called an
 "aggregate" if the compilation and its resulting copyright are not
 used to limit the access or legal rights of the compilation's users
 beyond what the individual works permit.  Inclusion of a covered work
 in an aggregate does not cause this License to apply to the other
 parts of the aggregate.
 
   6. Conveying Non-Source Forms.
 
   You may convey a covered work in object code form under the terms
 of sections 4 and 5, provided that you also convey the
 machine-readable Corresponding Source under the terms of this License,
 in one of these ways:
 
     a) Convey the object code in, or embodied in, a physical product
     (including a physical distribution medium), accompanied by the
     Corresponding Source fixed on a durable physical medium
     customarily used for software interchange.
 
     b) Convey the object code in, or embodied in, a physical product
     (including a physical distribution medium), accompanied by a
     written offer, valid for at least three years and valid for as
     long as you offer spare parts or customer support for that product
     model, to give anyone who possesses the object code either (1) a
     copy of the Corresponding Source for all the software in the
     product that is covered by this License, on a durable physical
     medium customarily used for software interchange, for a price no
     more than your reasonable cost of physically performing this
     conveying of source, or (2) access to copy the
     Corresponding Source from a network server at no charge.
 
     c) Convey individual copies of the object code with a copy of the
     written offer to provide the Corresponding Source.  This
     alternative is allowed only occasionally and noncommercially, and
     only if you received the object code with such an offer, in accord
     with subsection 6b.
 
     d) Convey the object code by offering access from a designated
     place (gratis or for a charge), and offer equivalent access to the
     Corresponding Source in the same way through the same place at no
     further charge.  You need not require recipients to copy the
     Corresponding Source along with the object code.  If the place to
     copy the object code is a network server, the Corresponding Source
     may be on a different server (operated by you or a third party)
     that supports equivalent copying facilities, provided you maintain
     clear directions next to the object code saying where to find the
     Corresponding Source.  Regardless of what server hosts the
     Corresponding Source, you remain obligated to ensure that it is
     available for as long as needed to satisfy these requirements.
 
     e) Convey the object code using peer-to-peer transmission, provided
     you inform other peers where the object code and Corresponding
     Source of the work are being offered to the general public at no
     charge under subsection 6d.
 
   A separable portion of the object code, whose source code is excluded
 from the Corresponding Source as a System Library, need not be
 included in conveying the object code work.
 
   A "User Product" is either (1) a "consumer product", which means any
 tangible personal property which is normally used for personal, family,
 or household purposes, or (2) anything designed or sold for incorporation
 into a dwelling.  In determining whether a product is a consumer product,
 doubtful cases shall be resolved in favor of coverage.  For a particular
 product received by a particular user, "normally used" refers to a
 typical or common use of that class of product, regardless of the status
 of the particular user or of the way in which the particular user
 actually uses, or expects or is expected to use, the product.  A product
 is a consumer product regardless of whether the product has substantial
 commercial, industrial or non-consumer uses, unless such uses represent
 the only significant mode of use of the product.
 
   "Installation Information" for a User Product means any methods,
 procedures, authorization keys, or other information required to install
 and execute modified versions of a covered work in that User Product from
 a modified version of its Corresponding Source.  The information must
 suffice to ensure that the continued functioning of the modified object
 code is in no case prevented or interfered with solely because
 modification has been made.
 
   If you convey an object code work under this section in, or with, or
 specifically for use in, a User Product, and the conveying occurs as
 part of a transaction in which the right of possession and use of the
 User Product is transferred to the recipient in perpetuity or for a
 fixed term (regardless of how the transaction is characterized), the
 Corresponding Source conveyed under this section must be accompanied
 by the Installation Information.  But this requirement does not apply
 if neither you nor any third party retains the ability to install
 modified object code on the User Product (for example, the work has
 been installed in ROM).
 
   The requirement to provide Installation Information does not include a
 requirement to continue to provide support service, warranty, or updates
 for a work that has been modified or installed by the recipient, or for
 the User Product in which it has been modified or installed.  Access to a
 network may be denied when the modification itself materially and
 adversely affects the operation of the network or violates the rules and
 protocols for communication across the network.
 
   Corresponding Source conveyed, and Installation Information provided,
 in accord with this section must be in a format that is publicly
 documented (and with an implementation available to the public in
 source code form), and must require no special password or key for
 unpacking, reading or copying.
 
   7. Additional Terms.
 
   "Additional permissions" are terms that supplement the terms of this
 License by making exceptions from one or more of its conditions.
 Additional permissions that are applicable to the entire Program shall
 be treated as though they were included in this License, to the extent
 that they are valid under applicable law.  If additional permissions
 apply only to part of the Program, that part may be used separately
 under those permissions, but the entire Program remains governed by
 this License without regard to the additional permissions.
 
   When you convey a copy of a covered work, you may at your option
 remove any additional permissions from that copy, or from any part of
 it.  (Additional permissions may be written to require their own
 removal in certain cases when you modify the work.)  You may place
 additional permissions on material, added by you to a covered work,
 for which you have or can give appropriate copyright permission.
 
   Notwithstanding any other provision of this License, for material you
 add to a covered work, you may (if authorized by the copyright holders of
 that material) supplement the terms of this License with terms:
 
     a) Disclaiming warranty or limiting liability differently from the
     terms of sections 15 and 16 of this License; or
 
     b) Requiring preservation of specified reasonable legal notices or
     author attributions in that material or in the Appropriate Legal
     Notices displayed by works containing it; or
 
     c) Prohibiting misrepresentation of the origin of that material, or
     requiring that modified versions of such material be marked in
     reasonable ways as different from the original version; or
 
     d) Limiting the use for publicity purposes of names of licensors or
     authors of the material; or
 
     e) Declining to grant rights under trademark law for use of some
     trade names, trademarks, or service marks; or
 
     f) Requiring indemnification of licensors and authors of that
     material by anyone who conveys the material (or modified versions of
     it) with contractual assumptions of liability to the recipient, for
     any liability that these contractual assumptions directly impose on
     those licensors and authors.
 
   All other non-permissive additional terms are considered "further
 restrictions" within the meaning of section 10.  If the Program as you
 received it, or any part of it, contains a notice stating that it is
 governed by this License along with a term that is a further
 restriction, you may remove that term.  If a license document contains
 a further restriction but permits relicensing or conveying under this
 License, you may add to a covered work material governed by the terms
 of that license document, provided that the further restriction does
 not survive such relicensing or conveying.
 
   If you add terms to a covered work in accord with this section, you
 must place, in the relevant source files, a statement of the
 additional terms that apply to those files, or a notice indicating
 where to find the applicable terms.
 
   Additional terms, permissive or non-permissive, may be stated in the
 form of a separately written license, or stated as exceptions;
 the above requirements apply either way.
 
   8. Termination.
 
   You may not propagate or modify a covered work except as expressly
 provided under this License.  Any attempt otherwise to propagate or
 modify it is void, and will automatically terminate your rights under
 this License (including any patent licenses granted under the third
 paragraph of section 11).
 
   However, if you cease all violation of this License, then your
 license from a particular copyright holder is reinstated (a)
 provisionally, unless and until the copyright holder explicitly and
 finally terminates your license, and (b) permanently, if the copyright
 holder fails to notify you of the violation by some reasonable means
 prior to 60 days after the cessation.
 
   Moreover, your license from a particular copyright holder is
 reinstated permanently if the copyright holder notifies you of the
 violation by some reasonable means, this is the first time you have
 received notice of violation of this License (for any work) from that
 copyright holder, and you cure the violation prior to 30 days after
 your receipt of the notice.
 
   Termination of your rights under this section does not terminate the
 licenses of parties who have received copies or rights from you under
 this License.  If your rights have been terminated and not permanently
 reinstated, you do not qualify to receive new licenses for the same
 material under section 10.
 
   9. Acceptance Not Required for Having Copies.
 
   You are not required to accept this License in order to receive or
 run a copy of the Program.  Ancillary propagation of a covered work
 occurring solely as a consequence of using peer-to-peer transmission
 to receive a copy likewise does not require acceptance.  However,
 nothing other than this License grants you permission to propagate or
 modify any covered work.  These actions infringe copyright if you do
 not accept this License.  Therefore, by modifying or propagating a
 covered work, you indicate your acceptance of this License to do so.
 
   10. Automatic Licensing of Downstream Recipients.
 
   Each time you convey a covered work, the recipient automatically
 receives a license from the original licensors, to run, modify and
 propagate that work, subject to this License.  You are not responsible
 for enforcing compliance by third parties with this License.
 
   An "entity transaction" is a transaction transferring control of an
 organization, or substantially all assets of one, or subdividing an
 organization, or merging organizations.  If propagation of a covered
 work results from an entity transaction, each party to that
 transaction who receives a copy of the work also receives whatever
 licenses to the work the party's predecessor in interest had or could
 give under the previous paragraph, plus a right to possession of the
 Corresponding Source of the work from the predecessor in interest, if
 the predecessor has it or can get it with reasonable efforts.
 
   You may not impose any further restrictions on the exercise of the
 rights granted or affirmed under this License.  For example, you may
 not impose a license fee, royalty, or other charge for exercise of
 rights granted under this License, and you may not initiate litigation
 (including a cross-claim or counterclaim in a lawsuit) alleging that
 any patent claim is infringed by making, using, selling, offering for
 sale, or importing the Program or any portion of it.
 
   11. Patents.
 
   A "contributor" is a copyright holder who authorizes use under this
 License of the Program or a work on which the Program is based.  The
 work thus licensed is called the contributor's "contributor version".
 
   A contributor's "essential patent claims" are all patent claims
 owned or controlled by the contributor, whether already acquired or
 hereafter acquired, that would be infringed by some manner, permitted
 by this License, of making, using, or selling its contributor version,
 but do not include claims that would be infringed only as a
 consequence of further modification of the contributor version.  For
 purposes of this definition, "control" includes the right to grant
 patent sublicenses in a manner consistent with the requirements of
 this License.
 
   Each contributor grants you a non-exclusive, worldwide, royalty-free
 patent license under the contributor's essential patent claims, to
 make, use, sell, offer for sale, import and otherwise run, modify and
 propagate the contents of its contributor version.
 
   In the following three paragraphs, a "patent license" is any express
 agreement or commitment, however denominated, not to enforce a patent
 (such as an express permission to practice a patent or covenant not to
 sue for patent infringement).  To "grant" such a patent license to a
 party means to make such an agreement or commitment not to enforce a
 patent against the party.
 
   If you convey a covered work, knowingly relying on a patent license,
 and the Corresponding Source of the work is not available for anyone
 to copy, free of charge and under the terms of this License, through a
 publicly available network server or other readily accessible means,
 then you must either (1) cause the Corresponding Source to be so
 available, or (2) arrange to deprive yourself of the benefit of the
 patent license for this particular work, or (3) arrange, in a manner
 consistent with the requirements of this License, to extend the patent
 license to downstream recipients.  "Knowingly relying" means you have
 actual knowledge that, but for the patent license, your conveying the
 covered work in a country, or your recipient's use of the covered work
 in a country, would infringe one or more identifiable patents in that
 country that you have reason to believe are valid.
 
   If, pursuant to or in connection with a single transaction or
 arrangement, you convey, or propagate by procuring conveyance of, a
 covered work, and grant a patent license to some of the parties
 receiving the covered work authorizing them to use, propagate, modify
 or convey a specific copy of the covered work, then the patent license
 you grant is automatically extended to all recipients of the covered
 work and works based on it.
 
   A patent license is "discriminatory" if it does not include within
 the scope of its coverage, prohibits the exercise of, or is
 conditioned on the non-exercise of one or more of the rights that are
 specifically granted under this License.  You may not convey a covered
 work if you are a party to an arrangement with a third party that is
 in the business of distributing software, under which you make payment
 to the third party based on the extent of your activity of conveying
 the work, and under which the third party grants, to any of the
 parties who would receive the covered work from you, a discriminatory
 patent license (a) in connection with copies of the covered work
 conveyed by you (or copies made from those copies), or (b) primarily
 for and in connection with specific products or compilations that
 contain the covered work, unless you entered into that arrangement,
 or that patent license was granted, prior to 28 March 2007.
 
   Nothing in this License shall be construed as excluding or limiting
 any implied license or other defenses to infringement that may
 otherwise be available to you under applicable patent law.
 
   12. No Surrender of Others' Freedom.
 
   If conditions are imposed on you (whether by court order, agreement or
 otherwise) that contradict the conditions of this License, they do not
 excuse you from the conditions of this License.  If you cannot convey a
 covered work so as to satisfy simultaneously your obligations under this
 License and any other pertinent obligations, then as a consequence you may
 not convey it at all.  For example, if you agree to terms that obligate you
 to collect a royalty for further conveying from those to whom you convey
 the Program, the only way you could satisfy both those terms and this
 License would be to refrain entirely from conveying the Program.
 
   13. Remote Network Interaction; Use with the GNU General Public License.
 
   Notwithstanding any other provision of this License, if you modify the
 Program, your modified version must prominently offer all users
 interacting with it remotely through a computer network (if your version
 supports such interaction) an opportunity to receive the Corresponding
 Source of your version by providing access to the Corresponding Source
 from a network server at no charge, through some standard or customary
 means of facilitating copying of software.  This Corresponding Source
 shall include the Corresponding Source for any work covered by version 3
 of the GNU General Public License that is incorporated pursuant to the
 following paragraph.
 
   Notwithstanding any other provision of this License, you have
 permission to link or combine any covered work with a work licensed
 under version 3 of the GNU General Public License into a single
 combined work, and to convey the resulting work.  The terms of this
 License will continue to apply to the part which is the covered work,
 but the work with which it is combined will remain governed by version
 3 of the GNU General Public License.
 
   14. Revised Versions of this License.
 
   The Free Software Foundation may publish revised and/or new versions of
 the GNU Affero General Public License from time to time.  Such new versions
 will be similar in spirit to the present version, but may differ in detail to
 address new problems or concerns.
 
   Each version is given a distinguishing version number.  If the
 Program specifies that a certain numbered version of the GNU Affero General
 Public License "or any later version" applies to it, you have the
 option of following the terms and conditions either of that numbered
 version or of any later version published by the Free Software
 Foundation.  If the Program does not specify a version number of the
 GNU Affero General Public License, you may choose any version ever published
 by the Free Software Foundation.
 
   If the Program specifies that a proxy can decide which future
 versions of the GNU Affero General Public License can be used, that proxy's
 public statement of acceptance of a version permanently authorizes you
 to choose that version for the Program.
 
   Later license versions may give you additional or different
 permissions.  However, no additional obligations are imposed on any
 author or copyright holder as a result of your choosing to follow a
 later version.
 
   15. Disclaimer of Warranty.
 
   THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
 APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
 HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
 OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
 THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
 IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
 ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
 
   16. Limitation of Liability.
 
   IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
 WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
 THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
 GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
 USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
 DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
 PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
 EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
 SUCH DAMAGES.
 
   17. Interpretation of Sections 15 and 16.
 
   If the disclaimer of warranty and limitation of liability provided
 above cannot be given local legal effect according to their terms,
 reviewing courts shall apply local law that most closely approximates
 an absolute waiver of all civil liability in connection with the
 Program, unless a warranty or assumption of liability accompanies a
 copy of the Program in return for a fee.
 
                      END OF TERMS AND CONDITIONS
 
             How to Apply These Terms to Your New Programs
 
   If you develop a new program, and you want it to be of the greatest
 possible use to the public, the best way to achieve this is to make it
 free software which everyone can redistribute and change under these terms.
 
   To do so, attach the following notices to the program.  It is safest
 to attach them to the start of each source file to most effectively
 state the exclusion of warranty; and each file should have at least
 the "copyright" line and a pointer to where the full notice is found.
 
     <one line to give the program's name and a brief idea of what it does.>
     Copyright (C) <year>  <name of author>
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU Affero General Public License as published by
     the Free Software Foundation, either version 3 of the License, or
     (at your option) any later version.
 
     This program is distributed in the hope that it will be useful,
     but WITHOUT ANY WARRANTY; without even the implied warranty of
     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
     GNU Affero General Public License for more details.
 
     You should have received a copy of the GNU Affero General Public License
     along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 Also add information on how to contact you by electronic and paper mail.
 
   If your software can interact with users remotely through a computer
 network, you should also make sure that it provides a way for users to
 get its source.  For example, if your program is a web application, its
 interface could display a "Source" link that leads users to an archive
 of the code.  There are many ways you could offer source, and different
 solutions will be better for different programs; see section 13 for the
 specific requirements.
 
   You should also get your employer (if you work as a programmer) or school,
 if any, to sign a "copyright disclaimer" for the program, if necessary.
 For more information on this, and how to apply and follow the GNU AGPL, see
 <http://www.gnu.org/licenses/>.

rhodecode/controllers/compare.py

@@ -1,267 +1,263 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2012-2016  RhodeCode GmbH
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License, version 3
 # (only), as published by the Free Software Foundation.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # This program is dual-licensed. If you wish to learn more about the
 # RhodeCode Enterprise Edition, including its added features, Support services,
 # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 """
 Compare controller for showing differences between two commits/refs/tags etc.
 """
 
 import logging
 
 from webob.exc import HTTPBadRequest
 from pylons import request, tmpl_context as c, url
 from pylons.controllers.util import redirect
 from pylons.i18n.translation import _
 
 from rhodecode.controllers.utils import parse_path_ref, get_commit_from_ref_name
 from rhodecode.lib import helpers as h
-from rhodecode.lib import diffs
+from rhodecode.lib import diffs, codeblocks
 from rhodecode.lib.auth import LoginRequired, HasRepoPermissionAnyDecorator
 from rhodecode.lib.base import BaseRepoController, render
 from rhodecode.lib.utils import safe_str
 from rhodecode.lib.utils2 import safe_unicode, str2bool
 from rhodecode.lib.vcs.exceptions import (
-    EmptyRepositoryError, RepositoryError, RepositoryRequirementError)
+    EmptyRepositoryError, RepositoryError, RepositoryRequirementError,
+    NodeDoesNotExistError)
 from rhodecode.model.db import Repository, ChangesetStatus
 
 log = logging.getLogger(__name__)
 
 
 class CompareController(BaseRepoController):
 
     def __before__(self):
         super(CompareController, self).__before__()
 
     def _get_commit_or_redirect(
             self, ref, ref_type, repo, redirect_after=True, partial=False):
         """
         This is a safe way to get a commit. If an error occurs it
         redirects to a commit with a proper message. If partial is set
         then it does not do redirect raise and throws an exception instead.
         """
         try:
             return get_commit_from_ref_name(repo, safe_str(ref), ref_type)
         except EmptyRepositoryError:
             if not redirect_after:
                 return repo.scm_instance().EMPTY_COMMIT
             h.flash(h.literal(_('There are no commits yet')),
                     category='warning')
             redirect(url('summary_home', repo_name=repo.repo_name))
 
         except RepositoryError as e:
             msg = safe_str(e)
             log.exception(msg)
             h.flash(msg, category='warning')
             if not partial:
                 redirect(h.url('summary_home', repo_name=repo.repo_name))
             raise HTTPBadRequest()
 
     @LoginRequired()
     @HasRepoPermissionAnyDecorator('repository.read', 'repository.write',
                                    'repository.admin')
     def index(self, repo_name):
         c.compare_home = True
         c.commit_ranges = []
-        c.files = []
+        c.diffset = None
         c.limited_diff = False
         source_repo = c.rhodecode_db_repo.repo_name
         target_repo = request.GET.get('target_repo', source_repo)
         c.source_repo = Repository.get_by_repo_name(source_repo)
         c.target_repo = Repository.get_by_repo_name(target_repo)
         c.source_ref = c.target_ref = _('Select commit')
         c.source_ref_type = ""
         c.target_ref_type = ""
         c.commit_statuses = ChangesetStatus.STATUSES
         c.preview_mode = False
         return render('compare/compare_diff.html')
 
     @LoginRequired()
     @HasRepoPermissionAnyDecorator('repository.read', 'repository.write',
                                    'repository.admin')
     def compare(self, repo_name, source_ref_type, source_ref,
                                  target_ref_type, target_ref):
         # source_ref will be evaluated in source_repo
         source_repo_name = c.rhodecode_db_repo.repo_name
         source_path, source_id = parse_path_ref(source_ref)
 
         # target_ref will be evaluated in target_repo
         target_repo_name = request.GET.get('target_repo', source_repo_name)
         target_path, target_id = parse_path_ref(target_ref)
 
         c.commit_statuses = ChangesetStatus.STATUSES
 
         # if merge is True
         #   Show what changes since the shared ancestor commit of target/source
         #   the source would get if it was merged with target. Only commits
         #   which are in target but not in source will be shown.
         merge = str2bool(request.GET.get('merge'))
         # if merge is False
         #   Show a raw diff of source/target refs even if no ancestor exists
 
 
         # c.fulldiff disables cut_off_limit
         c.fulldiff = str2bool(request.GET.get('fulldiff'))
 
         # if partial, returns just compare_commits.html (commits log)
         partial = request.is_xhr
 
         # swap url for compare_diff page
         c.swap_url = h.url(
             'compare_url',
             repo_name=target_repo_name,
             source_ref_type=target_ref_type,
             source_ref=target_ref,
             target_repo=source_repo_name,
             target_ref_type=source_ref_type,
             target_ref=source_ref,
             merge=merge and '1' or '')
 
         source_repo = Repository.get_by_repo_name(source_repo_name)
         target_repo = Repository.get_by_repo_name(target_repo_name)
 
         if source_repo is None:
             msg = _('Could not find the original repo: %(repo)s') % {
                 'repo': source_repo}
 
             log.error(msg)
             h.flash(msg, category='error')
             return redirect(url('compare_home', repo_name=c.repo_name))
 
         if target_repo is None:
             msg = _('Could not find the other repo: %(repo)s') % {
                 'repo': target_repo_name}
             log.error(msg)
             h.flash(msg, category='error')
             return redirect(url('compare_home', repo_name=c.repo_name))
 
         source_alias = source_repo.scm_instance().alias
         target_alias = target_repo.scm_instance().alias
         if source_alias != target_alias:
             msg = _('The comparison of two different kinds of remote repos '
                     'is not available')
             log.error(msg)
             h.flash(msg, category='error')
             return redirect(url('compare_home', repo_name=c.repo_name))
 
         source_commit = self._get_commit_or_redirect(
             ref=source_id, ref_type=source_ref_type, repo=source_repo,
             partial=partial)
         target_commit = self._get_commit_or_redirect(
             ref=target_id, ref_type=target_ref_type, repo=target_repo,
             partial=partial)
 
         c.compare_home = False
         c.source_repo = source_repo
         c.target_repo = target_repo
         c.source_ref = source_ref
         c.target_ref = target_ref
         c.source_ref_type = source_ref_type
         c.target_ref_type = target_ref_type
 
         source_scm = source_repo.scm_instance()
         target_scm = target_repo.scm_instance()
 
         pre_load = ["author", "branch", "date", "message"]
         c.ancestor = None
         try:
             c.commit_ranges = source_scm.compare(
                 source_commit.raw_id, target_commit.raw_id,
                 target_scm, merge, pre_load=pre_load)
             if merge:
                 c.ancestor = source_scm.get_common_ancestor(
                     source_commit.raw_id, target_commit.raw_id, target_scm)
         except RepositoryRequirementError:
             msg = _('Could not compare repos with different '
                     'large file settings')
             log.error(msg)
             if partial:
                 return msg
             h.flash(msg, category='error')
             return redirect(url('compare_home', repo_name=c.repo_name))
 
         c.statuses = c.rhodecode_db_repo.statuses(
             [x.raw_id for x in c.commit_ranges])
 
         if partial: # for PR ajax commits loader
             if not c.ancestor:
                 return '' # cannot merge if there is no ancestor
             return render('compare/compare_commits.html')
 
         if c.ancestor:
             # case we want a simple diff without incoming commits,
             # previewing what will be merged.
             # Make the diff on target repo (which is known to have target_ref)
             log.debug('Using ancestor %s as source_ref instead of %s'
                       % (c.ancestor, source_ref))
             source_repo = target_repo
             source_commit = target_repo.get_commit(commit_id=c.ancestor)
 
         # diff_limit will cut off the whole diff if the limit is applied
         # otherwise it will just hide the big files from the front-end
         diff_limit = self.cut_off_limit_diff
         file_limit = self.cut_off_limit_file
 
         log.debug('calculating diff between '
                   'source_ref:%s and target_ref:%s for repo `%s`',
                   source_commit, target_commit,
                   safe_unicode(source_repo.scm_instance().path))
 
         if source_commit.repository != target_commit.repository:
             msg = _(
                 "Repositories unrelated. "
                 "Cannot compare commit %(commit1)s from repository %(repo1)s "
                 "with commit %(commit2)s from repository %(repo2)s.") % {
                     'commit1': h.show_id(source_commit),
                     'repo1': source_repo.repo_name,
                     'commit2': h.show_id(target_commit),
                     'repo2': target_repo.repo_name,
                 }
             h.flash(msg, category='error')
             raise HTTPBadRequest()
 
         txtdiff = source_repo.scm_instance().get_diff(
             commit1=source_commit, commit2=target_commit,
             path1=source_path, path=target_path)
         diff_processor = diffs.DiffProcessor(
-            txtdiff, format='gitdiff', diff_limit=diff_limit,
+            txtdiff, format='newdiff', diff_limit=diff_limit,
             file_limit=file_limit, show_full_diff=c.fulldiff)
         _parsed = diff_processor.prepare()
 
-        c.limited_diff = False
-        if isinstance(_parsed, diffs.LimitedDiffContainer):
-            c.limited_diff = True
+        def _node_getter(commit):
+            """ Returns a function that returns a node for a commit or None """
+            def get_node(fname):
+                try:
+                    return commit.get_node(fname)
+                except NodeDoesNotExistError:
+                    return None
+            return get_node
 
-        c.files = []
-        c.changes = {}
-        c.lines_added = 0
-        c.lines_deleted = 0
-        for f in _parsed:
-            st = f['stats']
-            if not st['binary']:
-                c.lines_added += st['added']
-                c.lines_deleted += st['deleted']
-            fid = h.FID('', f['filename'])
-            c.files.append([fid, f['operation'], f['filename'], f['stats'], f])
-            htmldiff = diff_processor.as_html(
-                enable_comments=False, parsed_lines=[f])
-            c.changes[fid] = [f['operation'], f['filename'], htmldiff, f]
+        c.diffset = codeblocks.DiffSet(
+            source_node_getter=_node_getter(source_commit),
+            target_node_getter=_node_getter(target_commit),
+        ).render_patchset(_parsed, source_ref, target_ref)
 
         c.preview_mode = merge
 
         return render('compare/compare_diff.html')

rhodecode/lib/codeblocks.py

@@ -1,214 +1,635 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2011-2016  RhodeCode GmbH
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License, version 3
 # (only), as published by the Free Software Foundation.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # This program is dual-licensed. If you wish to learn more about the
 # RhodeCode Enterprise Edition, including its added features, Support services,
 # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 import logging
+import difflib
 from itertools import groupby
 
 from pygments import lex
 from pygments.formatters.html import _get_ttype_class as pygment_token_class
-from rhodecode.lib.helpers import get_lexer_for_filenode, html_escape
+from rhodecode.lib.helpers import (
+    get_lexer_for_filenode, get_lexer_safe, html_escape)
 from rhodecode.lib.utils2 import AttributeDict
 from rhodecode.lib.vcs.nodes import FileNode
+from rhodecode.lib.diff_match_patch import diff_match_patch
+from rhodecode.lib.diffs import LimitedDiffContainer
 from pygments.lexers import get_lexer_by_name
 
 plain_text_lexer = get_lexer_by_name(
     'text', stripall=False, stripnl=False, ensurenl=False)
 
 
 log = logging.getLogger()
 
 
 def filenode_as_lines_tokens(filenode, lexer=None):
     lexer = lexer or get_lexer_for_filenode(filenode)
     log.debug('Generating file node pygment tokens for %s, %s', lexer, filenode)
-    tokens = tokenize_string(filenode.content, get_lexer_for_filenode(filenode))
+    tokens = tokenize_string(filenode.content, lexer)
     lines = split_token_stream(tokens, split_string='\n')
     rv = list(lines)
     return rv
 
 
 def tokenize_string(content, lexer):
     """
     Use pygments to tokenize some content based on a lexer
     ensuring all original new lines and whitespace is preserved
     """
 
     lexer.stripall = False
     lexer.stripnl = False
     lexer.ensurenl = False
     for token_type, token_text in lex(content, lexer):
         yield pygment_token_class(token_type), token_text
 
 
 def split_token_stream(tokens, split_string=u'\n'):
     """
     Take a list of (TokenType, text) tuples and split them by a string
 
     >>> split_token_stream([(TEXT, 'some\ntext'), (TEXT, 'more\n')])
     [(TEXT, 'some'), (TEXT, 'text'),
      (TEXT, 'more'), (TEXT, 'text')]
     """
 
     buffer = []
     for token_class, token_text in tokens:
         parts = token_text.split(split_string)
         for part in parts[:-1]:
             buffer.append((token_class, part))
             yield buffer
             buffer = []
 
         buffer.append((token_class, parts[-1]))
 
     if buffer:
         yield buffer
 
 
 def filenode_as_annotated_lines_tokens(filenode):
     """
     Take a file node and return a list of annotations => lines, if no annotation
     is found, it will be None.
 
     eg:
 
     [
         (annotation1, [
             (1, line1_tokens_list),
             (2, line2_tokens_list),
         ]),
         (annotation2, [
             (3, line1_tokens_list),
         ]),
         (None, [
             (4, line1_tokens_list),
         ]),
         (annotation1, [
             (5, line1_tokens_list),
             (6, line2_tokens_list),
         ])
     ]
     """
 
     commit_cache = {} # cache commit_getter lookups
 
     def _get_annotation(commit_id, commit_getter):
         if commit_id not in commit_cache:
             commit_cache[commit_id] = commit_getter()
         return commit_cache[commit_id]
 
     annotation_lookup = {
         line_no: _get_annotation(commit_id, commit_getter)
         for line_no, commit_id, commit_getter, line_content
         in filenode.annotate
     }
 
     annotations_lines = ((annotation_lookup.get(line_no), line_no, tokens)
                           for line_no, tokens
                           in enumerate(filenode_as_lines_tokens(filenode), 1))
 
     grouped_annotations_lines = groupby(annotations_lines, lambda x: x[0])
 
     for annotation, group in grouped_annotations_lines:
         yield (
             annotation, [(line_no, tokens)
                           for (_, line_no, tokens) in group]
         )
 
 
 def render_tokenstream(tokenstream):
     result = []
     for token_class, token_ops_texts in rollup_tokenstream(tokenstream):
 
         if token_class:
             result.append(u'<span class="%s">' % token_class)
         else:
             result.append(u'<span>')
 
         for op_tag, token_text in token_ops_texts:
 
             if op_tag:
                 result.append(u'<%s>' % op_tag)
 
             escaped_text = html_escape(token_text)
-            escaped_text = escaped_text.replace('\n', '<nl>\n</nl>')
+
+            # TODO: dan: investigate showing hidden characters like space/nl/tab
+            # escaped_text = escaped_text.replace(' ', '<sp> </sp>')
+            # escaped_text = escaped_text.replace('\n', '<nl>\n</nl>')
+            # escaped_text = escaped_text.replace('\t', '<tab>\t</tab>')
 
             result.append(escaped_text)
 
             if op_tag:
                 result.append(u'</%s>' % op_tag)
 
         result.append(u'</span>')
 
     html = ''.join(result)
     return html
 
 
 def rollup_tokenstream(tokenstream):
     """
     Group a token stream of the format:
 
         ('class', 'op', 'text')
     or
         ('class', 'text')
 
     into
 
         [('class1',
             [('op1', 'text'),
              ('op2', 'text')]),
          ('class2',
             [('op3', 'text')])]
 
     This is used to get the minimal tags necessary when
     rendering to html eg for a token stream ie.
 
     <span class="A"><ins>he</ins>llo</span>
     vs
     <span class="A"><ins>he</ins></span><span class="A">llo</span>
 
     If a 2 tuple is passed in, the output op will be an empty string.
 
     eg:
 
     >>> rollup_tokenstream([('classA', '',      'h'),
                             ('classA', 'del',   'ell'),
                             ('classA', '',      'o'),
                             ('classB', '',      ' '),
                             ('classA', '',      'the'),
                             ('classA', '',      're'),
                             ])
 
     [('classA', [('', 'h'), ('del', 'ell'), ('', 'o')],
      ('classB', [('', ' ')],
      ('classA', [('', 'there')]]
 
     """
     if tokenstream and len(tokenstream[0]) == 2:
         tokenstream = ((t[0], '', t[1]) for t in tokenstream)
 
     result = []
     for token_class, op_list in groupby(tokenstream, lambda t: t[0]):
         ops = []
         for token_op, token_text_list in groupby(op_list, lambda o: o[1]):
             text_buffer = []
             for t_class, t_op, t_text in token_text_list:
                 text_buffer.append(t_text)
             ops.append((token_op, ''.join(text_buffer)))
         result.append((token_class, ops))
     return result
+
+
+def tokens_diff(old_tokens, new_tokens, use_diff_match_patch=True):
+    """
+    Converts a list of (token_class, token_text) tuples to a list of
+    (token_class, token_op, token_text) tuples where token_op is one of
+    ('ins', 'del', '')
+
+    :param old_tokens: list of (token_class, token_text) tuples of old line
+    :param new_tokens: list of (token_class, token_text) tuples of new line
+    :param use_diff_match_patch: boolean, will use google's diff match patch
+        library which has options to 'smooth' out the character by character
+        differences making nicer ins/del blocks
+    """
+
+    old_tokens_result = []
+    new_tokens_result = []
+
+    similarity = difflib.SequenceMatcher(None,
+        ''.join(token_text for token_class, token_text in old_tokens),
+        ''.join(token_text for token_class, token_text in new_tokens)
+    ).ratio()
+
+    if similarity < 0.6: # return, the blocks are too different
+        for token_class, token_text in old_tokens:
+            old_tokens_result.append((token_class, '', token_text))
+        for token_class, token_text in new_tokens:
+            new_tokens_result.append((token_class, '', token_text))
+        return old_tokens_result, new_tokens_result, similarity
+
+    token_sequence_matcher = difflib.SequenceMatcher(None,
+        [x[1] for x in old_tokens],
+        [x[1] for x in new_tokens])
+
+    for tag, o1, o2, n1, n2 in token_sequence_matcher.get_opcodes():
+        # check the differences by token block types first to give a more
+        # nicer "block" level replacement vs character diffs
+
+        if tag == 'equal':
+            for token_class, token_text in old_tokens[o1:o2]:
+                old_tokens_result.append((token_class, '', token_text))
+            for token_class, token_text in new_tokens[n1:n2]:
+                new_tokens_result.append((token_class, '', token_text))
+        elif tag == 'delete':
+            for token_class, token_text in old_tokens[o1:o2]:
+                old_tokens_result.append((token_class, 'del', token_text))
+        elif tag == 'insert':
+            for token_class, token_text in new_tokens[n1:n2]:
+                new_tokens_result.append((token_class, 'ins', token_text))
+        elif tag == 'replace':
+            # if same type token blocks must be replaced, do a diff on the
+            # characters in the token blocks to show individual changes
+
+            old_char_tokens = []
+            new_char_tokens = []
+            for token_class, token_text in old_tokens[o1:o2]:
+                for char in token_text:
+                    old_char_tokens.append((token_class, char))
+
+            for token_class, token_text in new_tokens[n1:n2]:
+                for char in token_text:
+                    new_char_tokens.append((token_class, char))
+
+            old_string = ''.join([token_text for
+                token_class, token_text in old_char_tokens])
+            new_string = ''.join([token_text for
+                token_class, token_text in new_char_tokens])
+
+            char_sequence = difflib.SequenceMatcher(
+                None, old_string, new_string)
+            copcodes = char_sequence.get_opcodes()
+            obuffer, nbuffer = [], []
+
+            if use_diff_match_patch:
+                dmp = diff_match_patch()
+                dmp.Diff_EditCost = 11 # TODO: dan: extract this to a setting
+                reps = dmp.diff_main(old_string, new_string)
+                dmp.diff_cleanupEfficiency(reps)
+
+                a, b = 0, 0
+                for op, rep in reps:
+                    l = len(rep)
+                    if op == 0:
+                        for i, c in enumerate(rep):
+                            obuffer.append((old_char_tokens[a+i][0], '', c))
+                            nbuffer.append((new_char_tokens[b+i][0], '', c))
+                        a += l
+                        b += l
+                    elif op == -1:
+                        for i, c in enumerate(rep):
+                            obuffer.append((old_char_tokens[a+i][0], 'del', c))
+                        a += l
+                    elif op == 1:
+                        for i, c in enumerate(rep):
+                            nbuffer.append((new_char_tokens[b+i][0], 'ins', c))
+                        b += l
+            else:
+                for ctag, co1, co2, cn1, cn2 in copcodes:
+                    if ctag == 'equal':
+                        for token_class, token_text in old_char_tokens[co1:co2]:
+                            obuffer.append((token_class, '', token_text))
+                        for token_class, token_text in new_char_tokens[cn1:cn2]:
+                            nbuffer.append((token_class, '', token_text))
+                    elif ctag == 'delete':
+                        for token_class, token_text in old_char_tokens[co1:co2]:
+                            obuffer.append((token_class, 'del', token_text))
+                    elif ctag == 'insert':
+                        for token_class, token_text in new_char_tokens[cn1:cn2]:
+                            nbuffer.append((token_class, 'ins', token_text))
+                    elif ctag == 'replace':
+                        for token_class, token_text in old_char_tokens[co1:co2]:
+                            obuffer.append((token_class, 'del', token_text))
+                        for token_class, token_text in new_char_tokens[cn1:cn2]:
+                            nbuffer.append((token_class, 'ins', token_text))
+
+            old_tokens_result.extend(obuffer)
+            new_tokens_result.extend(nbuffer)
+
+    return old_tokens_result, new_tokens_result, similarity
+
+
+class DiffSet(object):
+    """
+    An object for parsing the diff result from diffs.DiffProcessor and
+    adding highlighting, side by side/unified renderings and line diffs
+    """
+
+    HL_REAL = 'REAL' # highlights using original file, slow
+    HL_FAST = 'FAST' # highlights using just the line, fast but not correct
+                     # in the case of multiline code
+    HL_NONE = 'NONE' # no highlighting, fastest
+
+    def __init__(self, highlight_mode=HL_REAL,
+                 source_node_getter=lambda filename: None,
+                 target_node_getter=lambda filename: None,
+                 source_nodes=None, target_nodes=None,
+                 max_file_size_limit=150 * 1024, # files over this size will
+                                                 # use fast highlighting
+                 ):
+
+        self.highlight_mode = highlight_mode
+        self.highlighted_filenodes = {}
+        self.source_node_getter = source_node_getter
+        self.target_node_getter = target_node_getter
+        self.source_nodes = source_nodes or {}
+        self.target_nodes = target_nodes or {}
+
+
+        self.max_file_size_limit = max_file_size_limit
+
+    def render_patchset(self, patchset, source_ref=None, target_ref=None):
+        diffset = AttributeDict(dict(
+            lines_added=0,
+            lines_deleted=0,
+            changed_files=0,
+            files=[],
+            limited_diff=isinstance(patchset, LimitedDiffContainer),
+            source_ref=source_ref,
+            target_ref=target_ref,
+        ))
+        for patch in patchset:
+            filediff = self.render_patch(patch)
+            filediff.diffset = diffset
+            diffset.files.append(filediff)
+            diffset.changed_files += 1
+            if not patch['stats']['binary']:
+                diffset.lines_added += patch['stats']['added']
+                diffset.lines_deleted += patch['stats']['deleted']
+
+        return diffset
+
+    _lexer_cache = {}
+    def _get_lexer_for_filename(self, filename):
+        # cached because we might need to call it twice for source/target
+        if filename not in self._lexer_cache:
+            self._lexer_cache[filename] = get_lexer_safe(filepath=filename)
+        return self._lexer_cache[filename]
+
+    def render_patch(self, patch):
+        log.debug('rendering diff for %r' % patch['filename'])
+
+        source_filename = patch['original_filename']
+        target_filename = patch['filename']
+
+        source_lexer = plain_text_lexer
+        target_lexer = plain_text_lexer
+
+        if not patch['stats']['binary']:
+            if self.highlight_mode == self.HL_REAL:
+                if (source_filename and patch['operation'] in ('D', 'M')
+                    and source_filename not in self.source_nodes):
+                        self.source_nodes[source_filename] = (
+                            self.source_node_getter(source_filename))
+
+                if (target_filename and patch['operation'] in ('A', 'M')
+                    and target_filename not in self.target_nodes):
+                        self.target_nodes[target_filename] = (
+                            self.target_node_getter(target_filename))
+
+            elif self.highlight_mode == self.HL_FAST:
+                source_lexer = self._get_lexer_for_filename(source_filename)
+                target_lexer = self._get_lexer_for_filename(target_filename)
+
+        source_file = self.source_nodes.get(source_filename, source_filename)
+        target_file = self.target_nodes.get(target_filename, target_filename)
+
+        source_filenode, target_filenode = None, None
+
+        # TODO: dan: FileNode.lexer works on the content of the file - which
+        # can be slow - issue #4289 explains a lexer clean up - which once
+        # done can allow caching a lexer for a filenode to avoid the file lookup
+        if isinstance(source_file, FileNode):
+            source_filenode = source_file
+            source_lexer = source_file.lexer
+        if isinstance(target_file, FileNode):
+            target_filenode = target_file
+            target_lexer = target_file.lexer
+
+        source_file_path, target_file_path = None, None
+
+        if source_filename != '/dev/null':
+            source_file_path = source_filename
+        if target_filename != '/dev/null':
+            target_file_path = target_filename
+
+        source_file_type = source_lexer.name
+        target_file_type = target_lexer.name
+
+        op_hunks = patch['chunks'][0]
+        hunks = patch['chunks'][1:]
+
+        filediff = AttributeDict({
+            'source_file_path': source_file_path,
+            'target_file_path': target_file_path,
+            'source_filenode': source_filenode,
+            'target_filenode': target_filenode,
+            'hunks': [],
+            'source_file_type': target_file_type,
+            'target_file_type': source_file_type,
+            'patch': patch,
+            'source_mode': patch['stats']['old_mode'],
+            'target_mode': patch['stats']['new_mode'],
+            'limited_diff': isinstance(patch, LimitedDiffContainer),
+            'diffset': self,
+        })
+
+        for hunk in hunks:
+            hunkbit = self.parse_hunk(hunk, source_file, target_file)
+            hunkbit.filediff = filediff
+            filediff.hunks.append(hunkbit)
+        return filediff
+
+    def parse_hunk(self, hunk, source_file, target_file):
+        result = AttributeDict(dict(
+            source_start=hunk['source_start'],
+            source_length=hunk['source_length'],
+            target_start=hunk['target_start'],
+            target_length=hunk['target_length'],
+            section_header=hunk['section_header'],
+            lines=[],
+        ))
+        before, after = [], []
+
+        for line in hunk['lines']:
+            if line['action'] == 'unmod':
+                result.lines.extend(
+                    self.parse_lines(before, after, source_file, target_file))
+                after.append(line)
+                before.append(line)
+            elif line['action'] == 'add':
+                after.append(line)
+            elif line['action'] == 'del':
+                before.append(line)
+            elif line['action'] == 'context-old':
+                before.append(line)
+            elif line['action'] == 'context-new':
+                after.append(line)
+
+        result.lines.extend(
+            self.parse_lines(before, after, source_file, target_file))
+        result.unified = self.as_unified(result.lines)
+        result.sideside = result.lines
+        return result
+
+    def parse_lines(self, before_lines, after_lines, source_file, target_file):
+        # TODO: dan: investigate doing the diff comparison and fast highlighting
+        # on the entire before and after buffered block lines rather than by
+        # line, this means we can get better 'fast' highlighting if the context
+        # allows it - eg.
+        # line 4: """
+        # line 5: this gets highlighted as a string
+        # line 6: """
+
+        lines = []
+        while before_lines or after_lines:
+            before, after = None, None
+            before_tokens, after_tokens = None, None
+
+            if before_lines:
+                before = before_lines.pop(0)
+            if after_lines:
+                after = after_lines.pop(0)
+
+            original = AttributeDict()
+            modified = AttributeDict()
+
+            if before:
+                before_tokens = self.get_line_tokens(
+                    line_text=before['line'], line_number=before['old_lineno'],
+                    file=source_file)
+                original.lineno = before['old_lineno']
+                original.content = before['line']
+                original.action = self.action_to_op(before['action'])
+
+            if after:
+                after_tokens = self.get_line_tokens(
+                    line_text=after['line'], line_number=after['new_lineno'],
+                    file=target_file)
+                modified.lineno = after['new_lineno']
+                modified.content = after['line']
+                modified.action = self.action_to_op(after['action'])
+
+
+            # diff the lines
+            if before_tokens and after_tokens:
+                o_tokens, m_tokens, similarity = tokens_diff(before_tokens, after_tokens)
+                original.content = render_tokenstream(o_tokens)
+                modified.content = render_tokenstream(m_tokens)
+            elif before_tokens:
+                original.content = render_tokenstream(
+                    [(x[0], '', x[1]) for x in before_tokens])
+            elif after_tokens:
+                modified.content = render_tokenstream(
+                    [(x[0], '', x[1]) for x in after_tokens])
+
+            lines.append(AttributeDict({
+                'original': original,
+                'modified': modified,
+            }))
+
+        return lines
+
+    def get_line_tokens(self, line_text, line_number, file=None):
+        filenode = None
+        filename = None
+
+        if isinstance(file, basestring):
+            filename = file
+        elif isinstance(file, FileNode):
+            filenode = file
+            filename = file.unicode_path
+
+        if self.highlight_mode == self.HL_REAL and filenode:
+            if line_number and file.size < self.max_file_size_limit:
+                return self.get_tokenized_filenode_line(file, line_number)
+
+        if self.highlight_mode in (self.HL_REAL, self.HL_FAST) and filename:
+            lexer = self._get_lexer_for_filename(filename)
+            return list(tokenize_string(line_text, lexer))
+
+        return list(tokenize_string(line_text, plain_text_lexer))
+
+    def get_tokenized_filenode_line(self, filenode, line_number):
+
+        if filenode not in self.highlighted_filenodes:
+            tokenized_lines = filenode_as_lines_tokens(filenode, filenode.lexer)
+            self.highlighted_filenodes[filenode] = tokenized_lines
+        return self.highlighted_filenodes[filenode][line_number - 1]
+
+    def action_to_op(self, action):
+        return {
+            'add': '+',
+            'del': '-',
+            'unmod': ' ',
+            'context-old': ' ',
+            'context-new': ' ',
+        }.get(action, action)
+
+    def as_unified(self, lines):
+        """ Return a generator that yields the lines of a diff in unified order """
+        def generator():
+            buf = []
+            for line in lines:
+
+                if buf and not line.original or line.original.action == ' ':
+                    for b in buf:
+                        yield b
+                    buf = []
+
+                if line.original:
+                    if line.original.action == ' ':
+                        yield (line.original.lineno, line.modified.lineno,
+                               line.original.action, line.original.content)
+                        continue
+
+                    if line.original.action == '-':
+                        yield (line.original.lineno, None,
+                               line.original.action, line.original.content)
+
+                    if line.modified.action == '+':
+                        buf.append((
+                            None, line.modified.lineno,
+                            line.modified.action, line.modified.content))
+                        continue
+
+                if line.modified:
+                    yield (None, line.modified.lineno,
+                           line.modified.action, line.modified.content)
+
+            for b in buf:
+                yield b
+
+        return generator()

rhodecode/lib/diffs.py

@@ -1,886 +1,1161 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2011-2016  RhodeCode GmbH
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License, version 3
 # (only), as published by the Free Software Foundation.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # This program is dual-licensed. If you wish to learn more about the
 # RhodeCode Enterprise Edition, including its added features, Support services,
 # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 
 """
 Set of diffing helpers, previously part of vcs
 """
 
 import collections
 import re
 import difflib
 import logging
 
 from itertools import tee, imap
 
 from pylons.i18n.translation import _
 
 from rhodecode.lib.vcs.exceptions import VCSError
 from rhodecode.lib.vcs.nodes import FileNode, SubModuleNode
 from rhodecode.lib.vcs.backends.base import EmptyCommit
 from rhodecode.lib.helpers import escape
 from rhodecode.lib.utils2 import safe_unicode
 
 log = logging.getLogger(__name__)
 
 # define max context, a file with more than this numbers of lines is unusable
 # in browser anyway
 MAX_CONTEXT = 1024 * 1014
 
 
 class OPS(object):
     ADD = 'A'
     MOD = 'M'
     DEL = 'D'
 
 
 def wrap_to_table(str_):
     return '''<table class="code-difftable">
                 <tr class="line no-comment">
                 <td class="add-comment-line tooltip" title="%s"><span class="add-comment-content"></span></td>
                 <td></td>
                 <td class="lineno new"></td>
                 <td class="code no-comment"><pre>%s</pre></td>
                 </tr>
               </table>''' % (_('Click to comment'), str_)
 
 
 def wrapped_diff(filenode_old, filenode_new, diff_limit=None, file_limit=None,
                  show_full_diff=False, ignore_whitespace=True, line_context=3,
                  enable_comments=False):
     """
     returns a wrapped diff into a table, checks for cut_off_limit for file and
     whole diff and presents proper message
     """
 
     if filenode_old is None:
         filenode_old = FileNode(filenode_new.path, '', EmptyCommit())
 
     if filenode_old.is_binary or filenode_new.is_binary:
         diff = wrap_to_table(_('Binary file'))
         stats = None
         size = 0
         data = None
 
     elif diff_limit != -1 and (diff_limit is None or
         (filenode_old.size < diff_limit and filenode_new.size < diff_limit)):
 
         f_gitdiff = get_gitdiff(filenode_old, filenode_new,
                                 ignore_whitespace=ignore_whitespace,
                                 context=line_context)
         diff_processor = DiffProcessor(
             f_gitdiff, format='gitdiff', diff_limit=diff_limit,
             file_limit=file_limit, show_full_diff=show_full_diff)
         _parsed = diff_processor.prepare()
 
         diff = diff_processor.as_html(enable_comments=enable_comments)
         stats = _parsed[0]['stats'] if _parsed else None
         size = len(diff or '')
         data = _parsed[0] if _parsed else None
     else:
         diff = wrap_to_table(_('Changeset was too big and was cut off, use '
                                'diff menu to display this diff'))
         stats = None
         size = 0
         data = None
     if not diff:
         submodules = filter(lambda o: isinstance(o, SubModuleNode),
                             [filenode_new, filenode_old])
         if submodules:
             diff = wrap_to_table(escape('Submodule %r' % submodules[0]))
         else:
             diff = wrap_to_table(_('No changes detected'))
 
     cs1 = filenode_old.commit.raw_id
     cs2 = filenode_new.commit.raw_id
 
     return size, cs1, cs2, diff, stats, data
 
 
 def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True, context=3):
     """
     Returns git style diff between given ``filenode_old`` and ``filenode_new``.
 
     :param ignore_whitespace: ignore whitespaces in diff
     """
     # make sure we pass in default context
     context = context or 3
     # protect against IntOverflow when passing HUGE context
     if context > MAX_CONTEXT:
         context = MAX_CONTEXT
 
     submodules = filter(lambda o: isinstance(o, SubModuleNode),
                         [filenode_new, filenode_old])
     if submodules:
         return ''
 
     for filenode in (filenode_old, filenode_new):
         if not isinstance(filenode, FileNode):
             raise VCSError(
                 "Given object should be FileNode object, not %s"
                 % filenode.__class__)
 
     repo = filenode_new.commit.repository
     old_commit = filenode_old.commit or repo.EMPTY_COMMIT
     new_commit = filenode_new.commit
 
     vcs_gitdiff = repo.get_diff(
         old_commit, new_commit, filenode_new.path,
         ignore_whitespace, context, path1=filenode_old.path)
     return vcs_gitdiff
 
 NEW_FILENODE = 1
 DEL_FILENODE = 2
 MOD_FILENODE = 3
 RENAMED_FILENODE = 4
 COPIED_FILENODE = 5
 CHMOD_FILENODE = 6
 BIN_FILENODE = 7
 
 
 class LimitedDiffContainer(object):
 
     def __init__(self, diff_limit, cur_diff_size, diff):
         self.diff = diff
         self.diff_limit = diff_limit
         self.cur_diff_size = cur_diff_size
 
     def __getitem__(self, key):
         return self.diff.__getitem__(key)
 
     def __iter__(self):
         for l in self.diff:
             yield l
 
 
 class Action(object):
     """
     Contains constants for the action value of the lines in a parsed diff.
     """
 
     ADD = 'add'
     DELETE = 'del'
     UNMODIFIED = 'unmod'
 
     CONTEXT = 'context'
+    CONTEXT_OLD = 'context-old'
+    CONTEXT_NEW = 'context-new'
 
 
 class DiffProcessor(object):
     """
     Give it a unified or git diff and it returns a list of the files that were
     mentioned in the diff together with a dict of meta information that
     can be used to render it in a HTML template.
 
     .. note:: Unicode handling
 
        The original diffs are a byte sequence and can contain filenames
        in mixed encodings. This class generally returns `unicode` objects
        since the result is intended for presentation to the user.
 
     """
     _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)')
     _newline_marker = re.compile(r'^\\ No newline at end of file')
 
     # used for inline highlighter word split
     _token_re = re.compile(r'()(&gt;|&lt;|&amp;|\W+?)')
 
     def __init__(self, diff, format='gitdiff', diff_limit=None,
                  file_limit=None, show_full_diff=True):
         """
         :param diff: A `Diff` object representing a diff from a vcs backend
         :param format: format of diff passed, `udiff` or `gitdiff`
         :param diff_limit: define the size of diff that is considered "big"
             based on that parameter cut off will be triggered, set to None
             to show full diff
         """
         self._diff = diff
         self._format = format
         self.adds = 0
         self.removes = 0
         # calculate diff size
         self.diff_limit = diff_limit
         self.file_limit = file_limit
         self.show_full_diff = show_full_diff
         self.cur_diff_size = 0
         self.parsed = False
         self.parsed_diff = []
 
         if format == 'gitdiff':
             self.differ = self._highlight_line_difflib
             self._parser = self._parse_gitdiff
         else:
             self.differ = self._highlight_line_udiff
-            self._parser = self._parse_udiff
+            self._parser = self._new_parse_gitdiff
 
     def _copy_iterator(self):
         """
         make a fresh copy of generator, we should not iterate thru
         an original as it's needed for repeating operations on
         this instance of DiffProcessor
         """
         self.__udiff, iterator_copy = tee(self.__udiff)
         return iterator_copy
 
     def _escaper(self, string):
         """
         Escaper for diff escapes special chars and checks the diff limit
 
         :param string:
         """
 
         self.cur_diff_size += len(string)
 
         if not self.show_full_diff and (self.cur_diff_size > self.diff_limit):
             raise DiffLimitExceeded('Diff Limit Exceeded')
 
         return safe_unicode(string)\
             .replace('&', '&amp;')\
             .replace('<', '&lt;')\
             .replace('>', '&gt;')
 
     def _line_counter(self, l):
         """
         Checks each line and bumps total adds/removes for this diff
 
         :param l:
         """
         if l.startswith('+') and not l.startswith('+++'):
             self.adds += 1
         elif l.startswith('-') and not l.startswith('---'):
             self.removes += 1
         return safe_unicode(l)
 
     def _highlight_line_difflib(self, line, next_):
         """
         Highlight inline changes in both lines.
         """
 
         if line['action'] == Action.DELETE:
             old, new = line, next_
         else:
             old, new = next_, line
 
         oldwords = self._token_re.split(old['line'])
         newwords = self._token_re.split(new['line'])
         sequence = difflib.SequenceMatcher(None, oldwords, newwords)
 
         oldfragments, newfragments = [], []
         for tag, i1, i2, j1, j2 in sequence.get_opcodes():
             oldfrag = ''.join(oldwords[i1:i2])
             newfrag = ''.join(newwords[j1:j2])
             if tag != 'equal':
                 if oldfrag:
                     oldfrag = '<del>%s</del>' % oldfrag
                 if newfrag:
                     newfrag = '<ins>%s</ins>' % newfrag
             oldfragments.append(oldfrag)
             newfragments.append(newfrag)
 
         old['line'] = "".join(oldfragments)
         new['line'] = "".join(newfragments)
 
     def _highlight_line_udiff(self, line, next_):
         """
         Highlight inline changes in both lines.
         """
         start = 0
         limit = min(len(line['line']), len(next_['line']))
         while start < limit and line['line'][start] == next_['line'][start]:
             start += 1
         end = -1
         limit -= start
         while -end <= limit and line['line'][end] == next_['line'][end]:
             end -= 1
         end += 1
         if start or end:
             def do(l):
                 last = end + len(l['line'])
                 if l['action'] == Action.ADD:
                     tag = 'ins'
                 else:
                     tag = 'del'
                 l['line'] = '%s<%s>%s</%s>%s' % (
                     l['line'][:start],
                     tag,
                     l['line'][start:last],
                     tag,
                     l['line'][last:]
                 )
             do(line)
             do(next_)
 
     def _clean_line(self, line, command):
         if command in ['+', '-', ' ']:
             # only modify the line if it's actually a diff thing
             line = line[1:]
         return line
 
     def _parse_gitdiff(self, inline_diff=True):
         _files = []
         diff_container = lambda arg: arg
 
         for chunk in self._diff.chunks():
             head = chunk.header
 
             diff = imap(self._escaper, chunk.diff.splitlines(1))
             raw_diff = chunk.raw
             limited_diff = False
             exceeds_limit = False
 
             op = None
             stats = {
                 'added': 0,
                 'deleted': 0,
                 'binary': False,
                 'ops': {},
             }
 
             if head['deleted_file_mode']:
                 op = OPS.DEL
                 stats['binary'] = True
                 stats['ops'][DEL_FILENODE] = 'deleted file'
 
             elif head['new_file_mode']:
                 op = OPS.ADD
                 stats['binary'] = True
                 stats['ops'][NEW_FILENODE] = 'new file %s' % head['new_file_mode']
             else:  # modify operation, can be copy, rename or chmod
 
                 # CHMOD
                 if head['new_mode'] and head['old_mode']:
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][CHMOD_FILENODE] = (
                         'modified file chmod %s => %s' % (
                             head['old_mode'], head['new_mode']))
                 # RENAME
                 if head['rename_from'] != head['rename_to']:
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][RENAMED_FILENODE] = (
                         'file renamed from %s to %s' % (
                             head['rename_from'], head['rename_to']))
                 # COPY
                 if head.get('copy_from') and head.get('copy_to'):
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][COPIED_FILENODE] = (
                         'file copied from %s to %s' % (
                             head['copy_from'], head['copy_to']))
 
                 # If our new parsed headers didn't match anything fallback to
                 # old style detection
                 if op is None:
                     if not head['a_file'] and head['b_file']:
                         op = OPS.ADD
                         stats['binary'] = True
                         stats['ops'][NEW_FILENODE] = 'new file'
 
                     elif head['a_file'] and not head['b_file']:
                         op = OPS.DEL
                         stats['binary'] = True
                         stats['ops'][DEL_FILENODE] = 'deleted file'
 
                 # it's not ADD not DELETE
                 if op is None:
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][MOD_FILENODE] = 'modified file'
 
             # a real non-binary diff
             if head['a_file'] or head['b_file']:
                 try:
                     raw_diff, chunks, _stats = self._parse_lines(diff)
                     stats['binary'] = False
                     stats['added'] = _stats[0]
                     stats['deleted'] = _stats[1]
                     # explicit mark that it's a modified file
                     if op == OPS.MOD:
                         stats['ops'][MOD_FILENODE] = 'modified file'
                     exceeds_limit = len(raw_diff) > self.file_limit
 
                     # changed from _escaper function so we validate size of
                     # each file instead of the whole diff
                     # diff will hide big files but still show small ones
                     # from my tests, big files are fairly safe to be parsed
                     # but the browser is the bottleneck
                     if not self.show_full_diff and exceeds_limit:
                         raise DiffLimitExceeded('File Limit Exceeded')
 
                 except DiffLimitExceeded:
                     diff_container = lambda _diff: \
                         LimitedDiffContainer(
                             self.diff_limit, self.cur_diff_size, _diff)
 
                     exceeds_limit = len(raw_diff) > self.file_limit
                     limited_diff = True
                     chunks = []
 
             else:  # GIT format binary patch, or possibly empty diff
                 if head['bin_patch']:
                     # we have operation already extracted, but we mark simply
                     # it's a diff we wont show for binary files
                     stats['ops'][BIN_FILENODE] = 'binary diff hidden'
                 chunks = []
 
             if chunks and not self.show_full_diff and op == OPS.DEL:
                 # if not full diff mode show deleted file contents
                 # TODO: anderson: if the view is not too big, there is no way
                 # to see the content of the file
                 chunks = []
 
             chunks.insert(0, [{
                                   'old_lineno': '',
                                   'new_lineno': '',
                                   'action': Action.CONTEXT,
                                   'line': msg,
                               } for _op, msg in stats['ops'].iteritems()
                               if _op not in [MOD_FILENODE]])
 
             _files.append({
                 'filename': safe_unicode(head['b_path']),
                 'old_revision': head['a_blob_id'],
                 'new_revision': head['b_blob_id'],
                 'chunks': chunks,
                 'raw_diff': safe_unicode(raw_diff),
                 'operation': op,
                 'stats': stats,
                 'exceeds_limit': exceeds_limit,
                 'is_limited_diff': limited_diff,
             })
 
         sorter = lambda info: {OPS.ADD: 0, OPS.MOD: 1,
                                OPS.DEL: 2}.get(info['operation'])
 
         if not inline_diff:
             return diff_container(sorted(_files, key=sorter))
 
         # highlight inline changes
         for diff_data in _files:
             for chunk in diff_data['chunks']:
                 lineiter = iter(chunk)
                 try:
                     while 1:
                         line = lineiter.next()
                         if line['action'] not in (
                                 Action.UNMODIFIED, Action.CONTEXT):
                             nextline = lineiter.next()
                             if nextline['action'] in ['unmod', 'context'] or \
                                nextline['action'] == line['action']:
                                 continue
                             self.differ(line, nextline)
                 except StopIteration:
                     pass
 
         return diff_container(sorted(_files, key=sorter))
 
-    def _parse_udiff(self, inline_diff=True):
-        raise NotImplementedError()
+
+    # FIXME: NEWDIFFS: dan: this replaces the old _escaper function
+    def _process_line(self, string):
+        """
+        Process a diff line, checks the diff limit
+
+        :param string:
+        """
+
+        self.cur_diff_size += len(string)
+
+        if not self.show_full_diff and (self.cur_diff_size > self.diff_limit):
+            raise DiffLimitExceeded('Diff Limit Exceeded')
+
+        return safe_unicode(string)
+
+    # FIXME: NEWDIFFS: dan: this replaces _parse_gitdiff
+    def _new_parse_gitdiff(self, inline_diff=True):
+        _files = []
+        diff_container = lambda arg: arg
+        for chunk in self._diff.chunks():
+            head = chunk.header
+            log.debug('parsing diff %r' % head)
+
+            diff = imap(self._process_line, chunk.diff.splitlines(1))
+            raw_diff = chunk.raw
+            limited_diff = False
+            exceeds_limit = False
+            # if 'empty_file_to_modify_and_rename' in head['a_path']:
+            #     1/0
+            op = None
+            stats = {
+                'added': 0,
+                'deleted': 0,
+                'binary': False,
+                'old_mode': None,
+                'new_mode': None,
+                'ops': {},
+            }
+            if head['old_mode']:
+                stats['old_mode'] = head['old_mode']
+            if head['new_mode']:
+                stats['new_mode'] = head['new_mode']
+            if head['b_mode']:
+                stats['new_mode'] = head['b_mode']
+
+            if head['deleted_file_mode']:
+                op = OPS.DEL
+                stats['binary'] = True
+                stats['ops'][DEL_FILENODE] = 'deleted file'
+
+            elif head['new_file_mode']:
+                op = OPS.ADD
+                stats['binary'] = True
+                stats['old_mode'] = None
+                stats['new_mode'] = head['new_file_mode']
+                stats['ops'][NEW_FILENODE] = 'new file %s' % head['new_file_mode']
+            else:  # modify operation, can be copy, rename or chmod
+
+                # CHMOD
+                if head['new_mode'] and head['old_mode']:
+                    op = OPS.MOD
+                    stats['binary'] = True
+                    stats['ops'][CHMOD_FILENODE] = (
+                        'modified file chmod %s => %s' % (
+                            head['old_mode'], head['new_mode']))
+
+                # RENAME
+                if head['rename_from'] != head['rename_to']:
+                    op = OPS.MOD
+                    stats['binary'] = True
+                    stats['renamed'] = (head['rename_from'], head['rename_to'])
+                    stats['ops'][RENAMED_FILENODE] = (
+                        'file renamed from %s to %s' % (
+                            head['rename_from'], head['rename_to']))
+                # COPY
+                if head.get('copy_from') and head.get('copy_to'):
+                    op = OPS.MOD
+                    stats['binary'] = True
+                    stats['copied'] = (head['copy_from'], head['copy_to'])
+                    stats['ops'][COPIED_FILENODE] = (
+                        'file copied from %s to %s' % (
+                            head['copy_from'], head['copy_to']))
 
+                # If our new parsed headers didn't match anything fallback to
+                # old style detection
+                if op is None:
+                    if not head['a_file'] and head['b_file']:
+                        op = OPS.ADD
+                        stats['binary'] = True
+                        stats['new_file'] = True
+                        stats['ops'][NEW_FILENODE] = 'new file'
+
+                    elif head['a_file'] and not head['b_file']:
+                        op = OPS.DEL
+                        stats['binary'] = True
+                        stats['ops'][DEL_FILENODE] = 'deleted file'
+
+                # it's not ADD not DELETE
+                if op is None:
+                    op = OPS.MOD
+                    stats['binary'] = True
+                    stats['ops'][MOD_FILENODE] = 'modified file'
+
+            # a real non-binary diff
+            if head['a_file'] or head['b_file']:
+                try:
+                    raw_diff, chunks, _stats = self._new_parse_lines(diff)
+                    stats['binary'] = False
+                    stats['added'] = _stats[0]
+                    stats['deleted'] = _stats[1]
+                    # explicit mark that it's a modified file
+                    if op == OPS.MOD:
+                        stats['ops'][MOD_FILENODE] = 'modified file'
+                    exceeds_limit = len(raw_diff) > self.file_limit
+
+                    # changed from _escaper function so we validate size of
+                    # each file instead of the whole diff
+                    # diff will hide big files but still show small ones
+                    # from my tests, big files are fairly safe to be parsed
+                    # but the browser is the bottleneck
+                    if not self.show_full_diff and exceeds_limit:
+                        raise DiffLimitExceeded('File Limit Exceeded')
+
+                except DiffLimitExceeded:
+                    diff_container = lambda _diff: \
+                        LimitedDiffContainer(
+                            self.diff_limit, self.cur_diff_size, _diff)
+
+                    exceeds_limit = len(raw_diff) > self.file_limit
+                    limited_diff = True
+                    chunks = []
+
+            else:  # GIT format binary patch, or possibly empty diff
+                if head['bin_patch']:
+                    # we have operation already extracted, but we mark simply
+                    # it's a diff we wont show for binary files
+                    stats['ops'][BIN_FILENODE] = 'binary diff hidden'
+                chunks = []
+
+            if chunks and not self.show_full_diff and op == OPS.DEL:
+                # if not full diff mode show deleted file contents
+                # TODO: anderson: if the view is not too big, there is no way
+                # to see the content of the file
+                chunks = []
+
+            chunks.insert(0, [{
+                                  'old_lineno': '',
+                                  'new_lineno': '',
+                                  'action': Action.CONTEXT,
+                                  'line': msg,
+                              } for _op, msg in stats['ops'].iteritems()
+                              if _op not in [MOD_FILENODE]])
+
+            original_filename = safe_unicode(head['a_path'])
+            _files.append({
+                'original_filename': original_filename,
+                'filename': safe_unicode(head['b_path']),
+                'old_revision': head['a_blob_id'],
+                'new_revision': head['b_blob_id'],
+                'chunks': chunks,
+                'raw_diff': safe_unicode(raw_diff),
+                'operation': op,
+                'stats': stats,
+                'exceeds_limit': exceeds_limit,
+                'is_limited_diff': limited_diff,
+            })
+
+
+        sorter = lambda info: {OPS.ADD: 0, OPS.MOD: 1,
+                               OPS.DEL: 2}.get(info['operation'])
+
+        return diff_container(sorted(_files, key=sorter))
+
+    # FIXME: NEWDIFFS: dan: this gets replaced by _new_parse_lines
     def _parse_lines(self, diff):
         """
         Parse the diff an return data for the template.
         """
 
         lineiter = iter(diff)
         stats = [0, 0]
         chunks = []
         raw_diff = []
 
         try:
             line = lineiter.next()
 
             while line:
                 raw_diff.append(line)
                 lines = []
                 chunks.append(lines)
 
                 match = self._chunk_re.match(line)
 
                 if not match:
                     break
 
                 gr = match.groups()
                 (old_line, old_end,
                  new_line, new_end) = [int(x or 1) for x in gr[:-1]]
                 old_line -= 1
                 new_line -= 1
 
                 context = len(gr) == 5
                 old_end += old_line
                 new_end += new_line
 
                 if context:
                     # skip context only if it's first line
                     if int(gr[0]) > 1:
                         lines.append({
                             'old_lineno': '...',
                             'new_lineno': '...',
                             'action':     Action.CONTEXT,
                             'line':       line,
                         })
 
                 line = lineiter.next()
 
                 while old_line < old_end or new_line < new_end:
                     command = ' '
                     if line:
                         command = line[0]
 
                     affects_old = affects_new = False
 
                     # ignore those if we don't expect them
                     if command in '#@':
                         continue
                     elif command == '+':
                         affects_new = True
                         action = Action.ADD
                         stats[0] += 1
                     elif command == '-':
                         affects_old = True
                         action = Action.DELETE
                         stats[1] += 1
                     else:
                         affects_old = affects_new = True
                         action = Action.UNMODIFIED
 
                     if not self._newline_marker.match(line):
                         old_line += affects_old
                         new_line += affects_new
                         lines.append({
                             'old_lineno':   affects_old and old_line or '',
                             'new_lineno':   affects_new and new_line or '',
                             'action':       action,
                             'line':         self._clean_line(line, command)
                         })
                         raw_diff.append(line)
 
                     line = lineiter.next()
 
                     if self._newline_marker.match(line):
                         # we need to append to lines, since this is not
                         # counted in the line specs of diff
                         lines.append({
                             'old_lineno':   '...',
                             'new_lineno':   '...',
                             'action':       Action.CONTEXT,
                             'line':         self._clean_line(line, command)
                         })
 
         except StopIteration:
             pass
         return ''.join(raw_diff), chunks, stats
 
+    # FIXME: NEWDIFFS: dan: this replaces _parse_lines
+    def _new_parse_lines(self, diff):
+        """
+        Parse the diff an return data for the template.
+        """
+
+        lineiter = iter(diff)
+        stats = [0, 0]
+        chunks = []
+        raw_diff = []
+
+        try:
+            line = lineiter.next()
+
+            while line:
+                raw_diff.append(line)
+                match = self._chunk_re.match(line)
+
+                if not match:
+                    break
+
+                gr = match.groups()
+                (old_line, old_end,
+                 new_line, new_end) = [int(x or 1) for x in gr[:-1]]
+
+                lines = []
+                hunk = {
+                    'section_header': gr[-1],
+                    'source_start': old_line,
+                    'source_length': old_end,
+                    'target_start': new_line,
+                    'target_length': new_end,
+                    'lines': lines,
+                }
+                chunks.append(hunk)
+
+                old_line -= 1
+                new_line -= 1
+
+                context = len(gr) == 5
+                old_end += old_line
+                new_end += new_line
+
+                line = lineiter.next()
+
+                while old_line < old_end or new_line < new_end:
+                    command = ' '
+                    if line:
+                        command = line[0]
+
+                    affects_old = affects_new = False
+
+                    # ignore those if we don't expect them
+                    if command in '#@':
+                        continue
+                    elif command == '+':
+                        affects_new = True
+                        action = Action.ADD
+                        stats[0] += 1
+                    elif command == '-':
+                        affects_old = True
+                        action = Action.DELETE
+                        stats[1] += 1
+                    else:
+                        affects_old = affects_new = True
+                        action = Action.UNMODIFIED
+
+                    if not self._newline_marker.match(line):
+                        old_line += affects_old
+                        new_line += affects_new
+                        lines.append({
+                            'old_lineno':   affects_old and old_line or '',
+                            'new_lineno':   affects_new and new_line or '',
+                            'action':       action,
+                            'line':         self._clean_line(line, command)
+                        })
+                        raw_diff.append(line)
+
+                    line = lineiter.next()
+
+                    if self._newline_marker.match(line):
+                        # we need to append to lines, since this is not
+                        # counted in the line specs of diff
+                        if affects_old:
+                            action = Action.CONTEXT_OLD
+                        elif affects_new:
+                            action = Action.CONTEXT_NEW
+                        else:
+                            raise Exception('invalid context for no newline')
+
+                        lines.append({
+                            'old_lineno':   None,
+                            'new_lineno':   None,
+                            'action':       action,
+                            'line':         self._clean_line(line, command)
+                        })
+
+        except StopIteration:
+            pass
+        return ''.join(raw_diff), chunks, stats
+
     def _safe_id(self, idstring):
         """Make a string safe for including in an id attribute.
 
         The HTML spec says that id attributes 'must begin with
         a letter ([A-Za-z]) and may be followed by any number
         of letters, digits ([0-9]), hyphens ("-"), underscores
         ("_"), colons (":"), and periods (".")'. These regexps
         are slightly over-zealous, in that they remove colons
         and periods unnecessarily.
 
         Whitespace is transformed into underscores, and then
         anything which is not a hyphen or a character that
         matches \w (alphanumerics and underscore) is removed.
 
         """
         # Transform all whitespace to underscore
         idstring = re.sub(r'\s', "_", '%s' % idstring)
         # Remove everything that is not a hyphen or a member of \w
         idstring = re.sub(r'(?!-)\W', "", idstring).lower()
         return idstring
 
     def prepare(self, inline_diff=True):
         """
         Prepare the passed udiff for HTML rendering.
 
         :return: A list of dicts with diff information.
         """
         parsed = self._parser(inline_diff=inline_diff)
         self.parsed = True
         self.parsed_diff = parsed
         return parsed
 
     def as_raw(self, diff_lines=None):
         """
         Returns raw diff as a byte string
         """
         return self._diff.raw
 
     def as_html(self, table_class='code-difftable', line_class='line',
                 old_lineno_class='lineno old', new_lineno_class='lineno new',
                 code_class='code', enable_comments=False, parsed_lines=None):
         """
         Return given diff as html table with customized css classes
         """
         def _link_to_if(condition, label, url):
             """
             Generates a link if condition is meet or just the label if not.
             """
 
             if condition:
                 return '''<a href="%(url)s" class="tooltip"
                 title="%(title)s">%(label)s</a>''' % {
                     'title': _('Click to select line'),
                     'url': url,
                     'label': label
                 }
             else:
                 return label
         if not self.parsed:
             self.prepare()
 
         diff_lines = self.parsed_diff
         if parsed_lines:
             diff_lines = parsed_lines
 
         _html_empty = True
         _html = []
         _html.append('''<table class="%(table_class)s">\n''' % {
             'table_class': table_class
         })
 
         for diff in diff_lines:
             for line in diff['chunks']:
                 _html_empty = False
                 for change in line:
                     _html.append('''<tr class="%(lc)s %(action)s">\n''' % {
                         'lc': line_class,
                         'action': change['action']
                     })
                     anchor_old_id = ''
                     anchor_new_id = ''
                     anchor_old = "%(filename)s_o%(oldline_no)s" % {
                         'filename': self._safe_id(diff['filename']),
                         'oldline_no': change['old_lineno']
                     }
                     anchor_new = "%(filename)s_n%(oldline_no)s" % {
                         'filename': self._safe_id(diff['filename']),
                         'oldline_no': change['new_lineno']
                     }
                     cond_old = (change['old_lineno'] != '...' and
                                 change['old_lineno'])
                     cond_new = (change['new_lineno'] != '...' and
                                 change['new_lineno'])
                     if cond_old:
                         anchor_old_id = 'id="%s"' % anchor_old
                     if cond_new:
                         anchor_new_id = 'id="%s"' % anchor_new
 
                     if change['action'] != Action.CONTEXT:
                         anchor_link = True
                     else:
                         anchor_link = False
 
                     ###########################################################
                     # COMMENT ICONS
                     ###########################################################
                     _html.append('''\t<td class="add-comment-line"><span class="add-comment-content">''')
 
                     if enable_comments and change['action'] != Action.CONTEXT:
                         _html.append('''<a href="#"><span class="icon-comment-add"></span></a>''')
 
                     _html.append('''</span></td><td class="comment-toggle tooltip" title="Toggle Comment Thread"><i class="icon-comment"></i></td>\n''')
 
                     ###########################################################
                     # OLD LINE NUMBER
                     ###########################################################
                     _html.append('''\t<td %(a_id)s class="%(olc)s">''' % {
                         'a_id': anchor_old_id,
                         'olc': old_lineno_class
                     })
 
                     _html.append('''%(link)s''' % {
                         'link': _link_to_if(anchor_link, change['old_lineno'],
                                             '#%s' % anchor_old)
                     })
                     _html.append('''</td>\n''')
                     ###########################################################
                     # NEW LINE NUMBER
                     ###########################################################
 
                     _html.append('''\t<td %(a_id)s class="%(nlc)s">''' % {
                         'a_id': anchor_new_id,
                         'nlc': new_lineno_class
                     })
 
                     _html.append('''%(link)s''' % {
                         'link': _link_to_if(anchor_link, change['new_lineno'],
                                             '#%s' % anchor_new)
                     })
                     _html.append('''</td>\n''')
                     ###########################################################
                     # CODE
                     ###########################################################
                     code_classes = [code_class]
                     if (not enable_comments or
                             change['action'] == Action.CONTEXT):
                         code_classes.append('no-comment')
                     _html.append('\t<td class="%s">' % ' '.join(code_classes))
                     _html.append('''\n\t\t<pre>%(code)s</pre>\n''' % {
                         'code': change['line']
                     })
 
                     _html.append('''\t</td>''')
                     _html.append('''\n</tr>\n''')
         _html.append('''</table>''')
         if _html_empty:
             return None
         return ''.join(_html)
 
     def stat(self):
         """
         Returns tuple of added, and removed lines for this instance
         """
         return self.adds, self.removes
 
     def get_context_of_line(
             self, path, diff_line=None, context_before=3, context_after=3):
         """
         Returns the context lines for the specified diff line.
 
         :type diff_line: :class:`DiffLineNumber`
         """
         assert self.parsed, "DiffProcessor is not initialized."
 
         if None not in diff_line:
             raise ValueError(
                 "Cannot specify both line numbers: {}".format(diff_line))
 
         file_diff = self._get_file_diff(path)
         chunk, idx = self._find_chunk_line_index(file_diff, diff_line)
 
         first_line_to_include = max(idx - context_before, 0)
         first_line_after_context = idx + context_after + 1
         context_lines = chunk[first_line_to_include:first_line_after_context]
 
         line_contents = [
             _context_line(line) for line in context_lines
             if _is_diff_content(line)]
         # TODO: johbo: Interim fixup, the diff chunks drop the final newline.
         # Once they are fixed, we can drop this line here.
         if line_contents:
             line_contents[-1] = (
                 line_contents[-1][0], line_contents[-1][1].rstrip('\n') + '\n')
         return line_contents
 
     def find_context(self, path, context, offset=0):
         """
         Finds the given `context` inside of the diff.
 
         Use the parameter `offset` to specify which offset the target line has
         inside of the given `context`. This way the correct diff line will be
         returned.
 
         :param offset: Shall be used to specify the offset of the main line
             within the given `context`.
         """
         if offset < 0 or offset >= len(context):
             raise ValueError(
                 "Only positive values up to the length of the context "
                 "minus one are allowed.")
 
         matches = []
         file_diff = self._get_file_diff(path)
 
         for chunk in file_diff['chunks']:
             context_iter = iter(context)
             for line_idx, line in enumerate(chunk):
                 try:
                     if _context_line(line) == context_iter.next():
                         continue
                 except StopIteration:
                     matches.append((line_idx, chunk))
                 context_iter = iter(context)
 
         # Increment position and triger StopIteration
         # if we had a match at the end
         line_idx += 1
         try:
             context_iter.next()
         except StopIteration:
             matches.append((line_idx, chunk))
 
         effective_offset = len(context) - offset
         found_at_diff_lines = [
             _line_to_diff_line_number(chunk[idx - effective_offset])
             for idx, chunk in matches]
 
         return found_at_diff_lines
 
     def _get_file_diff(self, path):
         for file_diff in self.parsed_diff:
             if file_diff['filename'] == path:
                 break
         else:
             raise FileNotInDiffException("File {} not in diff".format(path))
         return file_diff
 
     def _find_chunk_line_index(self, file_diff, diff_line):
         for chunk in file_diff['chunks']:
             for idx, line in enumerate(chunk):
                 if line['old_lineno'] == diff_line.old:
                     return chunk, idx
                 if line['new_lineno'] == diff_line.new:
                     return chunk, idx
         raise LineNotInDiffException(
             "The line {} is not part of the diff.".format(diff_line))
 
 
 def _is_diff_content(line):
     return line['action'] in (
         Action.UNMODIFIED, Action.ADD, Action.DELETE)
 
 
 def _context_line(line):
     return (line['action'], line['line'])
 
 
 DiffLineNumber = collections.namedtuple('DiffLineNumber', ['old', 'new'])
 
 
 def _line_to_diff_line_number(line):
     new_line_no = line['new_lineno'] or None
     old_line_no = line['old_lineno'] or None
     return DiffLineNumber(old=old_line_no, new=new_line_no)
 
 
 class FileNotInDiffException(Exception):
     """
     Raised when the context for a missing file is requested.
 
     If you request the context for a line in a file which is not part of the
     given diff, then this exception is raised.
     """
 
 
 class LineNotInDiffException(Exception):
     """
     Raised when the context for a missing line is requested.
 
     If you request the context for a line in a file and this line is not
     part of the given diff, then this exception is raised.
     """
 
 
 class DiffLimitExceeded(Exception):
     pass

rhodecode/lib/vcs/backends/git/diff.py

@@ -1,47 +1,49 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2014-2016  RhodeCode GmbH
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License, version 3
 # (only), as published by the Free Software Foundation.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # This program is dual-licensed. If you wish to learn more about the
 # RhodeCode Enterprise Edition, including its added features, Support services,
 # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 """
 GIT diff module
 """
 
 import re
 
 from rhodecode.lib.vcs.backends import base
 
 
 class GitDiff(base.Diff):
 
     _header_re = re.compile(r"""
         #^diff[ ]--git
             [ ]"?a/(?P<a_path>.+?)"?[ ]"?b/(?P<b_path>.+?)"?\n
-        (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%\n
-           ^rename[ ]from[ ](?P<rename_from>[^\r\n]+)\n
-           ^rename[ ]to[ ](?P<rename_to>[^\r\n]+)(?:\n|$))?
         (?:^old[ ]mode[ ](?P<old_mode>\d+)\n
            ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))?
+        (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%(?:\n|$))?
+        (?:^rename[ ]from[ ](?P<rename_from>[^\r\n]+)\n
+           ^rename[ ]to[ ](?P<rename_to>[^\r\n]+)(?:\n|$))?
+        (?:^copy[ ]from[ ](?P<copy_from>[^\r\n]+)\n
+           ^copy[ ]to[ ](?P<copy_to>[^\r\n]+)(?:\n|$))?
         (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))?
         (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))?
         (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+)
             \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))?
         (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))?
         (?:^---[ ](a/(?P<a_file>.+)|/dev/null)(?:\n|$))?
         (?:^\+\+\+[ ](b/(?P<b_file>.+)|/dev/null)(?:\n|$))?
     """, re.VERBOSE | re.MULTILINE)

rhodecode/public/css/buttons.less

@@ -1,381 +1,389 b''
 
 
 //BUTTONS
 button,
 .btn,
 input[type="button"] {
     -webkit-appearance: none;
     display: inline-block;
     margin: 0 @padding/3 0 0;
     padding: @button-padding;
     text-align: center;
     font-size: @basefontsize;
     line-height: 1em;
     font-family: @text-light;
     text-decoration: none;
     text-shadow: none;
     color: @grey4;
     background-color: white;
     background-image: none;
     border: none;
     .border ( @border-thickness-buttons, @grey4 );
     .border-radius (@border-radius);
     cursor: pointer;
     white-space: nowrap;
     -webkit-transition: background .3s,color .3s;
        -moz-transition: background .3s,color .3s;
          -o-transition: background .3s,color .3s;
             transition: background .3s,color .3s;
 
     a {
         display: block;
         margin: 0;
         padding: 0;
         color: inherit;
         text-decoration: none;
 
         &:hover {
             text-decoration: none;
         }
     }
 
     &:focus,
     &:active {
         outline:none;
     }
     &:hover {
         color: white;
         background-color: @grey4;
     }
 
     .icon-remove-sign {
         display: none;
     }
 
     //disabled buttons
     //last; overrides any other styles
     &:disabled {
         opacity: .7;
         cursor: auto;
         background-color: white;
         color: @grey4;
         text-shadow: none;
     }
 
 }
 
 
 .btn-default {
     .border ( @border-thickness-buttons, @rcblue );
     background-image: none;
     color: @rcblue;
 
     a {
         color: @rcblue;
     }
 
     &:hover,
     &.active {
         color: white;
         background-color: @rcdarkblue;
         .border ( @border-thickness, @rcdarkblue );
 
         a {
             color: white;
         }
     }
     &:disabled {
         .border ( @border-thickness-buttons, @grey4 );
         background-color: none;
     }
 }
 
 .btn-primary,
 .btn-small, /* TODO: anderson: remove .btn-small to not mix with the new btn-sm */
 .btn-success {
     .border ( @border-thickness, @rcblue );
     background-color: @rcblue;
     color: white;
 
     a {
         color: white;
     }
 
     &:hover,
     &.active {
         .border ( @border-thickness, @rcdarkblue );
         color: white;
         background-color: @rcdarkblue;
 
         a {
             color: white;
         }
     }
     &:disabled {
         background-color: @rcblue;
     }
 }
 
 .btn-secondary {
     &:extend(.btn-default);
 
     background-color: white;
 
     &:focus {
         outline: 0;
     }
 
     &:hover {
         &:extend(.btn-default:hover);
     }
 
     &.btn-link {
         &:extend(.btn-link);
         color: @rcblue;
     }
 
     &:disabled {
         color: @rcblue;
         background-color: white;
     }
 }
 
 .btn-warning,
 .btn-danger,
 .revoke_perm,
 .btn-x,
 .form .action_button.btn-x   {
     .border ( @border-thickness, @alert2 );
     background-color: white;
     color: @alert2;
 
     a {
         color: @alert2;
     }
 
     &:hover,
     &.active {
         .border ( @border-thickness, @alert2 );
         color: white;
         background-color: @alert2;
 
         a {
             color: white;
         }
     }
 
     i {
         display:none;
     }
 
     &:disabled {
         background-color: white;
         color: @alert2;
     }
 }
 
 .btn-sm,
 .btn-mini,
 .field-sm .btn {
     padding: @padding/3;
 }
 
 .btn-xs {
     padding: @padding/4;
 }
 
 .btn-lg {
     padding: @padding * 1.2;
 }
 
+.btn-group {
+    display: inline-block;
+    .btn {
+        float: left;
+        margin: 0 0 0 -1px;
+    }
+}
+
 .btn-link {
     background: transparent;
     border: none;
     padding: 0;
     color: @rcblue;
 
     &:hover {
         background: transparent;
         border: none;
         color: @rcdarkblue;
     }
 
     &:disabled {
         color: @grey4;
     }
 
     // TODO: johbo: Check if we can avoid this, indicates that the structure
     // is not yet good.
     // lisa: The button CSS reflects the button HTML; both need a cleanup.
     &.btn-danger {
         color: @alert2;
 
         &:hover {
             color: darken(@alert2,30%);
         }
 
         &:disabled {
             color: @alert2;
         }
     }
 }
 
 .btn-social {
     &:extend(.btn-default);
     margin: 5px 5px 5px 0px;
     min-width: 150px;
 }
 
 // TODO: johbo: check these exceptions
 
 .links {
 
     .btn + .btn {
         margin-top: @padding;
     }
 }
 
 
 .action_button {
     display:inline;
     margin: 0;
     padding: 0 1em 0 0;
     font-size: inherit;
     color: @rcblue;
     border: none;
     .border-radius (0);
     background-color: transparent;
 
     &:last-child {
         border: none;
     }
 
     &:hover {
         color: @rcdarkblue;
         background-color: transparent;
         border: none;
     }
 }
 .grid_delete {
     .action_button {
         border: none;
     }
 }
 
 
 // TODO: johbo: Form button tweaks, check if we can use the classes instead
 input[type="submit"] {
     &:extend(.btn-primary);
 
     &:focus {
         outline: 0;
     }
 
     &:hover {
         &:extend(.btn-primary:hover);
     }
 
     &.btn-link {
         &:extend(.btn-link);
         color: @rcblue;
 
         &:disabled {
             color: @rcblue;
             background-color: transparent;
         }
     }
 
     &:disabled {
         .border ( @border-thickness-buttons, @rcblue );
         background-color: @rcblue;
         color: white;
     }
 }
 
 input[type="reset"] {
     &:extend(.btn-default);
 
     // TODO: johbo: Check if this tweak can be avoided.
     background: transparent;
 
     &:focus {
         outline: 0;
     }
 
     &:hover {
         &:extend(.btn-default:hover);
     }
 
     &.btn-link {
         &:extend(.btn-link);
         color: @rcblue;
 
         &:disabled {
             border: none;
         }
     }
 
     &:disabled {
         .border ( @border-thickness-buttons, @rcblue );
         background-color: white;
         color: @rcblue;
     }
 }
 
 input[type="submit"],
 input[type="reset"] {
     &.btn-danger {
         &:extend(.btn-danger);
     
         &:focus {
             outline: 0;
         }
     
         &:hover {
             &:extend(.btn-danger:hover);
         }
     
         &.btn-link {
             &:extend(.btn-link);
             color: @alert2;
 
             &:hover {
                 color: darken(@alert2,30%);
             }
         }
 
         &:disabled {
             color: @alert2;
             background-color: white;
         }
     }
     &.btn-danger-action {
         .border ( @border-thickness, @alert2 );
         background-color: @alert2;
         color: white;
 
         a {
             color: white;
         }
 
         &:hover {
             background-color: darken(@alert2,20%);
         }
 
         &.active {
             .border ( @border-thickness, @alert2 );
             color: white;
             background-color: @alert2;
 
             a {
                 color: white;
             }
         }
 
         &:disabled {
             background-color: white;
             color: @alert2;
         }
     }
 }
 

rhodecode/public/css/code-block.less

@@ -1,753 +1,1005 b''
 // Default styles
 
 .diff-collapse {
     margin: @padding 0;
     text-align: right;
 }
 
 .diff-container {
     margin-bottom: @space;
 
     .diffblock {
         margin-bottom: @space;
     }
 
     &.hidden {
         display: none;
         overflow: hidden;
     }
 }
 
 .compare_view_files {
 
     .diff-container {
 
         .diffblock {
             margin-bottom: 0;
         }
     }
 }
 
 div.diffblock .sidebyside {
  background: #ffffff;
 }
 
 div.diffblock {
     overflow-x: auto;
     overflow-y: hidden;
     clear: both;
     padding: 0px;
     background: @grey6;
     border: @border-thickness solid @grey5;
     -webkit-border-radius: @border-radius @border-radius 0px 0px;
     border-radius: @border-radius @border-radius 0px 0px;
 
 
     .comments-number {
         float: right;
     }
 
     // BEGIN CODE-HEADER STYLES
 
     .code-header {
         background: @grey6;
         padding: 10px 0 10px 0;
         height: auto;
         width: 100%;
 
         .hash {
             float: left;
             padding: 2px 0 0 2px;
         }
 
         .date {
             float: left;
             text-transform: uppercase;
             padding: 4px 0px 0px 2px;
         }
 
         div {
             margin-left: 4px;
         }
 
         div.compare_header {
             min-height: 40px;
             margin: 0;
             padding: 0 @padding;
 
             .drop-menu {
                 float:left;
                 display: block;
                 margin:0 0 @padding 0;
             }
 
             .compare-label {
                 float: left;
                 clear: both;
                 display: inline-block;
                 min-width: 5em;
                 margin: 0;
                 padding: @button-padding @button-padding @button-padding 0;
                 font-family: @text-semibold;
             }
 
             .compare-buttons {
                 float: left;
                 margin: 0;
                 padding: 0 0 @padding;
 
                 .btn {
                     margin: 0 @padding 0 0;
                 }
             }
         }
 
     }
 
     .parents {
         float: left;
         width: 100px;
         font-weight: 400;
         vertical-align: middle;
         padding: 0px 2px 0px 2px;
         background-color: @grey6;
 
         #parent_link {
            margin: 00px 2px;
 
            &.double {
                margin: 0px 2px;
             }
 
             &.disabled{
                 margin-right: @padding;
             }
         }
     }
 
     .children {
         float: right;
         width: 100px;
         font-weight: 400;
         vertical-align: middle;
         text-align: right;
         padding: 0px 2px 0px 2px;
         background-color: @grey6;
 
         #child_link {
            margin: 0px 2px;
 
            &.double {
                margin: 0px 2px;
             }
 
             &.disabled{
                 margin-right: @padding;
             }
         }
     }
 
     .changeset_header {
         height: 16px;
 
         & > div{
             margin-right: @padding;
        }
     }
 
     .changeset_file {
         text-align: left;
         float: left;
         padding: 0;
 
         a{
             display: inline-block;
             margin-right: 0.5em;
         }
 
        #selected_mode{
             margin-left: 0;
        }
     }
 
     .diff-menu-wrapper {
         float: left;
     }
 
     .diff-menu {
         position: absolute;
         background: none repeat scroll 0 0 #FFFFFF;
         border-color: #003367 @grey3 @grey3;
         border-right: 1px solid @grey3;
         border-style: solid solid solid;
         border-width: @border-thickness;
         box-shadow: 2px 8px 4px rgba(0, 0, 0, 0.2);
         margin-top: 5px;
         margin-left: 1px;
     }
 
     .diff-actions, .editor-actions {
         float: left;
 
         input{
             margin: 0 0.5em 0 0;
         }
     }
 
     // END CODE-HEADER STYLES
 
     // BEGIN CODE-BODY STYLES
 
     .code-body {
         background: white;
         padding: 0;
         background-color: #ffffff;
         position: relative;
         max-width: none;
         box-sizing: border-box;
         // TODO: johbo: Parent has overflow: auto, this forces the child here
         // to have the intended size and to scroll. Should be simplified.
         width: 100%;
         overflow-x: auto;
     }
 
     pre.raw {
         background: white;
         color: @grey1;
     }
     // END CODE-BODY STYLES
 
 }
 
 
 table.code-difftable {
     border-collapse: collapse;
     width: 99%;
     border-radius: 0px !important;
 
      td {
         padding: 0 !important;
         background: none !important;
         border: 0 !important;
     }
 
     .context {
         background: none repeat scroll 0 0 #DDE7EF;
     }
 
     .add {
         background: none repeat scroll 0 0 #DDFFDD;
 
         ins {
             background: none repeat scroll 0 0 #AAFFAA;
             text-decoration: none;
         }
     }
 
     .del {
         background: none repeat scroll 0 0 #FFDDDD;
 
         del {
             background: none repeat scroll 0 0 #FFAAAA;
             text-decoration: none;
         }
     }
 
     /** LINE NUMBERS **/
     .lineno {
         padding-left: 2px !important;
         padding-right: 2px;
         text-align: right;
         width: 32px;
         -moz-user-select: none;
         -webkit-user-select: none;
         border-right: @border-thickness solid @grey5 !important;
         border-left: 0px solid #CCC !important;
         border-top: 0px solid #CCC !important;
         border-bottom: none !important;
 
         a {
             &:extend(pre);
             text-align: right;
             padding-right: 2px;
             cursor: pointer;
             display: block;
             width: 32px;
         }
     }
 
     .context {
         cursor: auto;
         &:extend(pre);
     }
 
     .lineno-inline {
         background: none repeat scroll 0 0 #FFF !important;
         padding-left: 2px;
         padding-right: 2px;
         text-align: right;
         width: 30px;
         -moz-user-select: none;
         -webkit-user-select: none;
     }
 
     /** CODE **/
     .code {
         display: block;
         width: 100%;
 
         td {
             margin: 0;
             padding: 0;
         }
 
         pre {
             margin: 0;
             padding: 0;
             margin-left: .5em;
         }
     }
 }
 
 
 // Comments
 
 div.comment:target {
     border-left: 6px solid @comment-highlight-color;
     padding-left: 3px;
     margin-left: -9px;
 }
 
 //TODO: anderson: can't get an absolute number out of anything, so had to put the
 //current values that might change. But to make it clear I put as a calculation
 @comment-max-width: 1065px;
 @pr-extra-margin: 34px;
 @pr-border-spacing: 4px;
 @pr-comment-width: @comment-max-width - @pr-extra-margin - @pr-border-spacing;
 
 // Pull Request
 .cs_files .code-difftable {
     border: @border-thickness solid @grey5; //borders only on PRs
 
     .comment-inline-form,
     div.comment {
         width: @pr-comment-width;
     }
 }
 
 // Changeset
 .code-difftable {
     .comment-inline-form,
     div.comment {
         width: @comment-max-width;
     }
 }
 
 //Style page
 @style-extra-margin: @sidebar-width + (@sidebarpadding * 3) + @padding;
 #style-page .code-difftable{
     .comment-inline-form,
     div.comment {
         width: @comment-max-width - @style-extra-margin;
     }
 }
 
 #context-bar > h2 {
     font-size: 20px;
 }
 
 #context-bar > h2> a {
     font-size: 20px;
 }
 // end of defaults
 
 .file_diff_buttons {
     padding: 0 0 @padding;
 
     .drop-menu {
         float: left;
         margin: 0 @padding 0 0;
     }
     .btn {
         margin: 0 @padding 0 0;
     }
 }
 
 .code-body.textarea.editor {
     max-width: none;
     padding: 15px;
 }
 
 td.injected_diff{
     max-width: 1178px;
     overflow-x: auto;
     overflow-y: hidden;
 
     div.diff-container,
     div.diffblock{
         max-width: 100%;
     }
 
     div.code-body {
         max-width: 1124px;
         overflow-x: auto;
         overflow-y: hidden;
         padding: 0;
     }
     div.diffblock {
         border: none;
     }
 
     &.inline-form {
         width: 99%
     }
  }
 
 
 table.code-difftable {
     width: 100%;
 }
 
 /** PYGMENTS COLORING **/
 div.codeblock {
 
     // TODO: johbo: Added interim to get rid of the margin around
     // Select2 widgets. This needs further cleanup.
     margin-top: @padding;
 
     overflow: auto;
     padding: 0px;
     border: @border-thickness solid @grey5;
     background: @grey6;
     .border-radius(@border-radius);
 
     #remove_gist {
         float: right;
     }
 
     .author {
         clear: both;
         vertical-align: middle;
         font-family: @text-bold;
     }
 
     .btn-mini {
         float: left;
         margin: 0 5px 0 0;
     }
 
     .code-header {
         padding: @padding;
         border-bottom: @border-thickness solid @grey5;
 
         .rc-user {
             min-width: 0;
             margin-right: .5em;
         }
 
         .stats {
             clear: both;
             margin: 0 0 @padding 0;
             padding: 0;
             .left {
                 float: left;
                 clear: left;
                 max-width: 75%;
                 margin: 0 0 @padding 0;
 
                 &.item {
                     margin-right: @padding;
                     &.last { border-right: none; }
                 }
             }
             .buttons { float: right; }
             .author {
                 height: 25px; margin-left: 15px; font-weight: bold;
             }
         }
 
         .commit {
             margin: 5px 0 0 26px;
             font-weight: normal;
             white-space: pre-wrap;
         }
     }
 
     .message {
         position: relative;
         margin: @padding;
 
         .codeblock-label {
             margin: 0 0 1em 0;
         }
     }
 
     .code-body {
         padding: @padding;
         background-color: #ffffff;
         min-width: 100%;
         box-sizing: border-box;
         // TODO: johbo: Parent has overflow: auto, this forces the child here
         // to have the intended size and to scroll. Should be simplified.
         width: 100%;
         overflow-x: auto;
     }
 }
 
 .code-highlighttable,
 div.codeblock {
 
     &.readme {
         background-color: white;
     }
 
     .markdown-block table {
         border-collapse: collapse;
 
         th,
         td {
             padding: .5em;
             border: @border-thickness solid @border-default-color;
         }
     }
 
     table {
         border: 0px;
         margin: 0;
         letter-spacing: normal;
 
 
         td {
             border: 0px;
             vertical-align: top;
         }
     }
 }
 
 div.codeblock .code-header .search-path { padding: 0 0 0 10px; }
 div.search-code-body {
     background-color: #ffffff; padding: 5px 0 5px 10px;
     pre {
         .match { background-color: #faffa6;}
         .break { display: block; width: 100%; background-color: #DDE7EF; color: #747474; }
     }
     .code-highlighttable {
         border-collapse: collapse;
 
         tr:hover {
             background: #fafafa;
         }
         td.code {
           padding-left: 10px;
         }
         td.line {
             border-right: 1px solid #ccc !important;
             padding-right: 10px;
             text-align: right;
             font-family: "Lucida Console",Monaco,monospace;
             span {
                 white-space: pre-wrap;
                 color: #666666;
             }
         }
     }
 }
 
 div.annotatediv { margin-left: 2px; margin-right: 4px; }
 .code-highlight {
     margin: 0; padding: 0; border-left: @border-thickness solid @grey5;
     pre, .linenodiv pre { padding: 0 5px; margin: 0; }
     pre div:target {background-color: @comment-highlight-color !important;}
 }
 
 .linenos a { text-decoration: none; }
 
 .CodeMirror-selected { background: @rchighlightblue; }
 .CodeMirror-focused .CodeMirror-selected { background: @rchighlightblue; }
 .CodeMirror ::selection { background: @rchighlightblue; }
 .CodeMirror ::-moz-selection { background: @rchighlightblue; }
 
 .code { display: block; border:0px !important; }
 .code-highlight, /* TODO: dan: merge codehilite into code-highlight */
 .codehilite {
     .hll { background-color: #ffffcc }
     .c { color: #408080; font-style: italic } /* Comment */
     .err, .codehilite .err { border: @border-thickness solid #FF0000 } /* Error */
     .k { color: #008000; font-weight: bold } /* Keyword */
     .o { color: #666666 } /* Operator */
     .cm { color: #408080; font-style: italic } /* Comment.Multiline */
     .cp { color: #BC7A00 } /* Comment.Preproc */
     .c1 { color: #408080; font-style: italic } /* Comment.Single */
     .cs { color: #408080; font-style: italic } /* Comment.Special */
     .gd { color: #A00000 } /* Generic.Deleted */
     .ge { font-style: italic } /* Generic.Emph */
     .gr { color: #FF0000 } /* Generic.Error */
     .gh { color: #000080; font-weight: bold } /* Generic.Heading */
     .gi { color: #00A000 } /* Generic.Inserted */
     .go { color: #808080 } /* Generic.Output */
     .gp { color: #000080; font-weight: bold } /* Generic.Prompt */
     .gs { font-weight: bold } /* Generic.Strong */
     .gu { color: #800080; font-weight: bold } /* Generic.Subheading */
     .gt { color: #0040D0 } /* Generic.Traceback */
     .kc { color: #008000; font-weight: bold } /* Keyword.Constant */
     .kd { color: #008000; font-weight: bold } /* Keyword.Declaration */
     .kn { color: #008000; font-weight: bold } /* Keyword.Namespace */
     .kp { color: #008000 } /* Keyword.Pseudo */
     .kr { color: #008000; font-weight: bold } /* Keyword.Reserved */
     .kt { color: #B00040 } /* Keyword.Type */
     .m { color: #666666 } /* Literal.Number */
     .s { color: #BA2121 } /* Literal.String */
     .na { color: #7D9029 } /* Name.Attribute */
     .nb { color: #008000 } /* Name.Builtin */
     .nc { color: #0000FF; font-weight: bold } /* Name.Class */
     .no { color: #880000 } /* Name.Constant */
     .nd { color: #AA22FF } /* Name.Decorator */
     .ni { color: #999999; font-weight: bold } /* Name.Entity */
     .ne { color: #D2413A; font-weight: bold } /* Name.Exception */
     .nf { color: #0000FF } /* Name.Function */
     .nl { color: #A0A000 } /* Name.Label */
     .nn { color: #0000FF; font-weight: bold } /* Name.Namespace */
     .nt { color: #008000; font-weight: bold } /* Name.Tag */
     .nv { color: #19177C } /* Name.Variable */
     .ow { color: #AA22FF; font-weight: bold } /* Operator.Word */
     .w { color: #bbbbbb } /* Text.Whitespace */
     .mf { color: #666666 } /* Literal.Number.Float */
     .mh { color: #666666 } /* Literal.Number.Hex */
     .mi { color: #666666 } /* Literal.Number.Integer */
     .mo { color: #666666 } /* Literal.Number.Oct */
     .sb { color: #BA2121 } /* Literal.String.Backtick */
     .sc { color: #BA2121 } /* Literal.String.Char */
     .sd { color: #BA2121; font-style: italic } /* Literal.String.Doc */
     .s2 { color: #BA2121 } /* Literal.String.Double */
     .se { color: #BB6622; font-weight: bold } /* Literal.String.Escape */
     .sh { color: #BA2121 } /* Literal.String.Heredoc */
     .si { color: #BB6688; font-weight: bold } /* Literal.String.Interpol */
     .sx { color: #008000 } /* Literal.String.Other */
     .sr { color: #BB6688 } /* Literal.String.Regex */
     .s1 { color: #BA2121 } /* Literal.String.Single */
     .ss { color: #19177C } /* Literal.String.Symbol */
     .bp { color: #008000 } /* Name.Builtin.Pseudo */
     .vc { color: #19177C } /* Name.Variable.Class */
     .vg { color: #19177C } /* Name.Variable.Global */
     .vi { color: #19177C } /* Name.Variable.Instance */
     .il { color: #666666 } /* Literal.Number.Integer.Long */
 }
 
 /* customized pre blocks for markdown/rst */
 pre.literal-block, .codehilite pre{
     padding: @padding;
     border: 1px solid @grey6;
     .border-radius(@border-radius);
     background-color: @grey7;
 }
 
 
 /* START NEW CODE BLOCK CSS */
 
 @cb-line-height: 18px;
 @cb-line-code-padding: 10px;
+@cb-text-padding: 5px;
 
+@diff-pill-padding: 2px 7px;
+
+input.diff-collapse-state {
+    display: none;
+
+    &:checked + .diff { /* file diff is collapsed */
+        .cb {
+            display: none
+        }
+        .diff-collapse-indicator {
+            border-width: 9px 0 9px 15.6px;
+            border-color: transparent transparent transparent #ccc;
+        }
+        .diff-menu {
+            display: none;
+        }
+        margin: -1px 0 0 0;
+    }
+
+    &+ .diff { /* file diff is expanded */
+        .diff-collapse-indicator {
+            border-width: 15.6px 9px 0 9px;
+            border-color: #ccc transparent transparent transparent;
+        }
+        .diff-menu {
+            display: block;
+        }
+        margin: 20px 0;
+    }
+}
+.diff {
+    border: 1px solid @grey5;
+
+    /* START OVERRIDES */
+    .code-highlight {
+        border: none;  // TODO: remove this border from the global
+                       // .code-highlight, it doesn't belong there
+    }
+    label {
+        margin: 0; // TODO: remove this margin definition from global label
+                   // it doesn't belong there - if margin on labels
+                   // are needed for a form they should be defined
+                   // in the form's class
+    }
+    /* END OVERRIDES */
+
+    * {
+        box-sizing: border-box;
+    }
+    .diff-anchor {
+        visibility: hidden;
+    }
+    &:hover {
+        .diff-anchor {
+            visibility: visible;
+        }
+    }
+
+    .diff-collapse-indicator {
+        width: 0;
+        height: 0;
+        border-style: solid;
+        float: left;
+        margin: 2px 2px 0 0;
+        cursor: pointer;
+    }
+
+    .diff-heading {
+        background: @grey7;
+        cursor: pointer;
+        display: block;
+        padding: 5px 10px;
+    }
+    .diff-heading:after {
+        content: "";
+        display: table;
+        clear: both;
+    }
+    .diff-heading:hover {
+        background: #e1e9f4 !important;
+    }
+
+    .diff-menu {
+        float: right;
+        a, button {
+            padding: 5px;
+            display: block;
+            float: left
+        }
+    }
+    .diff-pill {
+        display: block;
+        float: left;
+        padding: @diff-pill-padding;
+    }
+    .diff-pill-group {
+        .diff-pill {
+            opacity: .8;
+            &:first-child {
+                border-radius: @border-radius 0 0 @border-radius;
+            }
+            &:last-child {
+                border-radius: 0 @border-radius @border-radius 0;
+            }
+            &:only-child {
+                border-radius: @border-radius;
+            }
+        }
+    }
+    .diff-pill {
+        &[op="name"] {
+            background: none;
+            color: @grey2;
+            opacity: 1;
+            color: white;
+        }
+        &[op="limited"] {
+            background: @grey2;
+            color: white;
+        }
+        &[op="binary"] {
+            background: @color7;
+            color: white;
+        }
+        &[op="modified"] {
+            background: @alert1;
+            color: white;
+        }
+        &[op="renamed"] {
+            background: @color4;
+            color: white;
+        }
+        &[op="mode"] {
+            background: @grey3;
+            color: white;
+        }
+        &[op="symlink"] {
+            background: @color8;
+            color: white;
+        }
+
+        &[op="added"] { /* added lines */
+            background: @alert1;
+            color: white;
+        }
+        &[op="deleted"] { /* deleted lines */
+            background: @alert2;
+            color: white;
+        }
+
+        &[op="created"] { /* created file */
+            background: @alert1;
+            color: white;
+        }
+        &[op="removed"] { /* deleted file */
+            background: @color5;
+            color: white;
+        }
+    }
+
+    .diff-collapse-button, .diff-expand-button {
+        cursor: pointer;
+    }
+    .diff-collapse-button {
+        display: inline;
+    }
+    .diff-expand-button {
+        display: none;
+    }
+    .diff-collapsed .diff-collapse-button {
+        display: none;
+    }
+    .diff-collapsed .diff-expand-button {
+        display: inline;
+    }
+}
 table.cb {
     width: 100%;
     border-collapse: collapse;
-    margin-bottom: 10px;
 
-    * {
-        box-sizing: border-box;
+    .cb-text {
+        padding: @cb-text-padding;
+    }
+    .cb-hunk {
+        padding: @cb-text-padding;
+    }
+    .cb-expand {
+        display: none;
+    }
+    .cb-collapse {
+        display: inline;
+    }
+    &.cb-collapsed {
+        .cb-line {
+            display: none;
+        }
+        .cb-expand {
+            display: inline;
+        }
+        .cb-collapse {
+            display: none;
+        }
     }
 
     /* intentionally general selector since .cb-line-selected must override it
        and they both use !important since the td itself may have a random color
        generated by annotation blocks. TLDR: if you change it, make sure
        annotated block selection and line selection in file view still work */
     .cb-line-fresh .cb-content {
         background: white !important;
     }
+    .cb-warning {
+        background: #fff4dd;
+    }
 
-    tr.cb-annotate {
+    &.cb-diff-sideside {
+        td {
+            &.cb-content {
+                width: 50%;
+            }
+        }
+    }
+
+    tr {
+        &.cb-annotate {
         border-top: 1px solid #eee;
 
         &+ .cb-line {
             border-top: 1px solid #eee;
         }
 
         &:first-child {
             border-top: none;
             &+ .cb-line {
                 border-top: none;
             }
         }
     }
 
+        &.cb-hunk {
+            font-family: @font-family-monospace;
+            color: rgba(0, 0, 0, 0.3);
+
+            td {
+                &:first-child {
+                    background: #edf2f9;
+                }
+                &:last-child {
+                    background: #f4f7fb;
+                }
+            }
+        }
+    }
+
     td {
         vertical-align: top;
         padding: 0;
 
         &.cb-content {
             font-size: 12.35px;
 
+            &.cb-line-selected .cb-code {
+                background: @comment-highlight-color !important;
+            }
+
             span.cb-code {
                 line-height: @cb-line-height;
                 padding-left: @cb-line-code-padding;
+                padding-right: @cb-line-code-padding;
                 display: block;
                 white-space: pre-wrap;
                 font-family: @font-family-monospace;
                 word-break: break-word;
             }
         }
 
         &.cb-lineno {
             padding: 0;
             width: 50px;
             color: rgba(0, 0, 0, 0.3);
             text-align: right;
             border-right: 1px solid #eee;
             font-family: @font-family-monospace;
 
             a::before {
                 content: attr(data-line-no);
             }
             &.cb-line-selected a {
                 background: @comment-highlight-color !important;
             }
 
             a {
                 display: block;
                 padding-right: @cb-line-code-padding;
+                padding-left: @cb-line-code-padding;
                 line-height: @cb-line-height;
                 color: rgba(0, 0, 0, 0.3);
             }
         }
 
-        &.cb-content {
-            &.cb-line-selected .cb-code {
-                background: @comment-highlight-color !important;
+        &.cb-empty {
+            background: @grey7;
+        }
+
+        ins {
+            color: black;
+            background: #a6f3a6;
+            text-decoration: none;
+        }
+        del {
+            color: black;
+            background: #f8cbcb;
+            text-decoration: none;
+        }
+        &.cb-addition {
+            background: #ecffec;
+
+            &.blob-lineno {
+                background: #ddffdd;
+            }
+        }
+        &.cb-deletion {
+            background: #ffecec;
+
+            &.blob-lineno {
+                background: #ffdddd;
             }
         }
 
         &.cb-annotate-info {
             width: 320px;
             min-width: 320px;
             max-width: 320px;
             padding: 5px 2px;
             font-size: 13px;
 
             strong.cb-annotate-message {
                 padding: 5px 0;
                 white-space: pre-line;
                 display: inline-block;
             }
             .rc-user {
                 float: none;
                 padding: 0 6px 0 17px;
                 min-width: auto;
                 min-height: auto;
             }
         }
 
         &.cb-annotate-revision {
             cursor: pointer;
             text-align: right;
         }
     }
 }

rhodecode/public/js/src/rhodecode.js

@@ -1,476 +1,492 b''
 // # Copyright (C) 2010-2016  RhodeCode GmbH
 // #
 // # This program is free software: you can redistribute it and/or modify
 // # it under the terms of the GNU Affero General Public License, version 3
 // # (only), as published by the Free Software Foundation.
 // #
 // # This program is distributed in the hope that it will be useful,
 // # but WITHOUT ANY WARRANTY; without even the implied warranty of
 // # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 // # GNU General Public License for more details.
 // #
 // # You should have received a copy of the GNU Affero General Public License
 // # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 // #
 // # This program is dual-licensed. If you wish to learn more about the
 // # RhodeCode Enterprise Edition, including its added features, Support services,
 // # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 /**
 RhodeCode JS Files
 **/
 
 if (typeof console == "undefined" || typeof console.log == "undefined"){
     console = { log: function() {} }
 }
 
 // TODO: move the following function to submodules
 
 /**
  * show more
  */
 var show_more_event = function(){
   $('table .show_more').click(function(e) {
     var cid = e.target.id.substring(1);
     var button = $(this);
     if (button.hasClass('open')) {
       $('#'+cid).hide();
       button.removeClass('open');
     } else {
       $('#'+cid).show();
       button.addClass('open one');
     }
   });
 };
 
 var compare_radio_buttons = function(repo_name, compare_ref_type){
     $('#compare_action').on('click', function(e){
         e.preventDefault();
 
         var source = $('input[name=compare_source]:checked').val();
         var target = $('input[name=compare_target]:checked').val();
         if(source && target){
             var url_data = {
                 repo_name: repo_name,
                 source_ref: source,
                 source_ref_type: compare_ref_type,
                 target_ref: target,
                 target_ref_type: compare_ref_type,
                 merge: 1
             };
             window.location = pyroutes.url('compare_url', url_data);
         }
     });
     $('.compare-radio-button').on('click', function(e){
         var source = $('input[name=compare_source]:checked').val();
         var target = $('input[name=compare_target]:checked').val();
         if(source && target){
             $('#compare_action').removeAttr("disabled");
             $('#compare_action').removeClass("disabled");
         }
     })
 };
 
 var showRepoSize = function(target, repo_name, commit_id, callback) {
     var container = $('#' + target);
     var url = pyroutes.url('repo_stats',
       {"repo_name": repo_name, "commit_id": commit_id});
 
     if (!container.hasClass('loaded')) {
         $.ajax({url: url})
             .complete(function (data) {
                 var responseJSON = data.responseJSON;
                 container.addClass('loaded');
                 container.html(responseJSON.size);
                 callback(responseJSON.code_stats)
             })
             .fail(function (data) {
                 console.log('failed to load repo stats');
             });
     }
 
 };
 
 var showRepoStats = function(target, data){
     var container = $('#' + target);
 
     if (container.hasClass('loaded')) {
         return
     }
 
     var total = 0;
     var no_data = true;
     var tbl = document.createElement('table');
     tbl.setAttribute('class', 'trending_language_tbl');
 
     $.each(data, function(key, val){
         total += val.count;
     });
 
     var sortedStats = [];
     for (var obj in data){
         sortedStats.push([obj, data[obj]])
     }
     var sortedData = sortedStats.sort(function (a, b) {
         return b[1].count - a[1].count
     });
     var cnt = 0;
     $.each(sortedData, function(idx, val){
         cnt += 1;
         no_data = false;
 
         var hide = cnt > 2;
         var tr = document.createElement('tr');
         if (hide) {
             tr.setAttribute('style', 'display:none');
             tr.setAttribute('class', 'stats_hidden');
         }
 
         var key = val[0];
         var obj = {"desc": val[1].desc, "count": val[1].count};
 
         var percentage = Math.round((obj.count / total * 100), 2);
 
         var td1 = document.createElement('td');
         td1.width = 300;
         var trending_language_label = document.createElement('div');
         trending_language_label.innerHTML = obj.desc + " (.{0})".format(key);
         td1.appendChild(trending_language_label);
 
         var td2 = document.createElement('td');
         var trending_language = document.createElement('div');
         var nr_files = obj.count +" "+ _ngettext('file', 'files', obj.count);
 
         trending_language.title = key + " " + nr_files;
 
         trending_language.innerHTML = "<span>" + percentage + "% " + nr_files
                 + "</span><b>" + percentage + "% " + nr_files + "</b>";
 
         trending_language.setAttribute("class", 'trending_language');
         $('b', trending_language)[0].style.width = percentage + "%";
         td2.appendChild(trending_language);
 
         tr.appendChild(td1);
         tr.appendChild(td2);
         tbl.appendChild(tr);
         if (cnt == 3) {
             var show_more = document.createElement('tr');
             var td = document.createElement('td');
             lnk = document.createElement('a');
 
             lnk.href = '#';
             lnk.innerHTML = _gettext('Show more');
             lnk.id = 'code_stats_show_more';
             td.appendChild(lnk);
 
             show_more.appendChild(td);
             show_more.appendChild(document.createElement('td'));
             tbl.appendChild(show_more);
         }
     });
 
     $(container).html(tbl);
     $(container).addClass('loaded');
 
     $('#code_stats_show_more').on('click', function (e) {
         e.preventDefault();
         $('.stats_hidden').each(function (idx) {
             $(this).css("display", "");
         });
         $('#code_stats_show_more').hide();
     });
 
 };
 
 
 // Toggle Collapsable Content
 function collapsableContent() {
 
     $('.collapsable-content').not('.no-hide').hide();
 
     $('.btn-collapse').unbind(); //in case we've been here before
     $('.btn-collapse').click(function() {
         var button = $(this);
         var togglename = $(this).data("toggle");
         $('.collapsable-content[data-toggle='+togglename+']').toggle();
         if ($(this).html()=="Show Less")
             $(this).html("Show More");
         else
             $(this).html("Show Less");
     });
 };
 
 var timeagoActivate = function() {
     $("time.timeago").timeago();
 };
 
 // Formatting values in a Select2 dropdown of commit references
 var formatSelect2SelectionRefs = function(commit_ref){
   var tmpl = '';
   if (!commit_ref.text || commit_ref.type === 'sha'){
     return commit_ref.text;
   }
   if (commit_ref.type === 'branch'){
     tmpl = tmpl.concat('<i class="icon-branch"></i> ');
   } else if (commit_ref.type === 'tag'){
     tmpl = tmpl.concat('<i class="icon-tag"></i> ');
   } else if (commit_ref.type === 'book'){
     tmpl = tmpl.concat('<i class="icon-bookmark"></i> ');
   }
   return tmpl.concat(commit_ref.text);
 };
 
 // takes a given html element and scrolls it down offset pixels
 function offsetScroll(element, offset){
     setTimeout(function(){
         var location = element.offset().top;
         // some browsers use body, some use html
         $('html, body').animate({ scrollTop: (location - offset) });
     }, 100);
 }
 
+// scroll an element `percent`% from the top of page in `time` ms
+function scrollToElement(element, percent, time) {
+    percent = (percent === undefined ? 25 : percent);
+    time = (time === undefined ? 100 : time);
+
+    var $element = $(element);
+    var elOffset = $element.offset().top;
+    var elHeight = $element.height();
+    var windowHeight = $(window).height();
+    var offset = elOffset;
+    if (elHeight < windowHeight) {
+        offset = elOffset - ((windowHeight / (100 / percent)) - (elHeight / 2));
+    }
+    setTimeout(function() {
+        $('html, body').animate({ scrollTop: offset});
+    }, time);
+}
+
 /**
  * global hooks after DOM is loaded
  */
 $(document).ready(function() {
     firefoxAnchorFix();
 
     $('.navigation a.menulink').on('click', function(e){
         var menuitem = $(this).parent('li');
         if (menuitem.hasClass('open')) {
             menuitem.removeClass('open');
         } else {
             menuitem.addClass('open');
             $(document).on('click', function(event) {
                 if (!$(event.target).closest(menuitem).length) {
                     menuitem.removeClass('open');
                 }
             });
         }
     });
     $('.compare_view_files').on(
         'mouseenter mouseleave', 'tr.line .lineno a',function(event) {
             if (event.type === "mouseenter") {
                 $(this).parents('tr.line').addClass('hover');
             } else {
                 $(this).parents('tr.line').removeClass('hover');
             }
         });
 
     $('.compare_view_files').on(
         'mouseenter mouseleave', 'tr.line .add-comment-line a',function(event){
             if (event.type === "mouseenter") {
                 $(this).parents('tr.line').addClass('commenting');
             } else {
                 $(this).parents('tr.line').removeClass('commenting');
             }
         });
 
     $('body').on( /* TODO: replace the $('.compare_view_files').on('click') below
                     when new diffs are integrated */
         'click', '.cb-lineno a', function(event) {
 
             if ($(this).attr('data-line-no') !== ""){
                 $('.cb-line-selected').removeClass('cb-line-selected');
                 var td = $(this).parent();
                 td.addClass('cb-line-selected'); // line number td
                 td.next().addClass('cb-line-selected'); // line content td
 
                 // Replace URL without jumping to it if browser supports.
                 // Default otherwise
                 if (history.pushState) {
                     var new_location = location.href.rstrip('#');
                     if (location.hash) {
                         new_location = new_location.replace(location.hash, "");
                     }
 
                     // Make new anchor url
                     new_location = new_location + $(this).attr('href');
                     history.pushState(true, document.title, new_location);
 
                     return false;
                 }
             }
         });
 
     $('.compare_view_files').on( /* TODO: replace this with .cb function above
                                     when new diffs are integrated */
         'click', 'tr.line .lineno a',function(event) {
             if ($(this).text() != ""){
                 $('tr.line').removeClass('selected');
                 $(this).parents("tr.line").addClass('selected');
 
                 // Replace URL without jumping to it if browser supports.
                 // Default otherwise
                 if (history.pushState) {
                     var new_location = location.href;
                     if (location.hash){
                         new_location = new_location.replace(location.hash, "");
                     }
 
                     // Make new anchor url
                     var new_location = new_location+$(this).attr('href');
                     history.pushState(true, document.title, new_location);
 
                     return false;
                 }
             }
         });
 
     $('.compare_view_files').on(
         'click', 'tr.line .add-comment-line a',function(event) {
             var tr = $(event.currentTarget).parents('tr.line')[0];
             injectInlineForm(tr);
             return false;
         });
 
     $('.collapse_file').on('click', function(e) {
         e.stopPropagation();
         if ($(e.target).is('a')) { return; }
         var node = $(e.delegateTarget).first();
         var icon = $($(node.children().first()).children().first());
         var id = node.attr('fid');
         var target = $('#'+id);
         var tr = $('#tr_'+id);
         var diff = $('#diff_'+id);
         if(node.hasClass('expand_file')){
             node.removeClass('expand_file');
             icon.removeClass('expand_file_icon');
             node.addClass('collapse_file');
             icon.addClass('collapse_file_icon');
             diff.show();
             tr.show();
             target.show();
         } else {
             node.removeClass('collapse_file');
             icon.removeClass('collapse_file_icon');
             node.addClass('expand_file');
             icon.addClass('expand_file_icon');
             diff.hide();
             tr.hide();
             target.hide();
         }
     });
 
     $('#expand_all_files').click(function() {
         $('.expand_file').each(function() {
             var node = $(this);
             var icon = $($(node.children().first()).children().first());
             var id = $(this).attr('fid');
             var target = $('#'+id);
             var tr = $('#tr_'+id);
             var diff = $('#diff_'+id);
             node.removeClass('expand_file');
             icon.removeClass('expand_file_icon');
             node.addClass('collapse_file');
             icon.addClass('collapse_file_icon');
             diff.show();
             tr.show();
             target.show();
         });
     });
 
     $('#collapse_all_files').click(function() {
         $('.collapse_file').each(function() {
             var node = $(this);
             var icon = $($(node.children().first()).children().first());
             var id = $(this).attr('fid');
             var target = $('#'+id);
             var tr = $('#tr_'+id);
             var diff = $('#diff_'+id);
             node.removeClass('collapse_file');
             icon.removeClass('collapse_file_icon');
             node.addClass('expand_file');
             icon.addClass('expand_file_icon');
             diff.hide();
             tr.hide();
             target.hide();
         });
     });
 
     // Mouse over behavior for comments and line selection
 
     // Select the line that comes from the url anchor
     // At the time of development, Chrome didn't seem to support jquery's :target
     // element, so I had to scroll manually
 
     if (location.hash) { /* TODO: dan: remove this and replace with code block
                             below when new diffs are ready */
         var result = splitDelimitedHash(location.hash);
         var loc  = result.loc;
         if (loc.length > 1){
             var lineno = $(loc+'.lineno');
             if (lineno.length > 0){
                 var tr = lineno.parents('tr.line');
                 tr.addClass('selected');
 
                 tr[0].scrollIntoView();
 
                 $.Topic('/ui/plugins/code/anchor_focus').prepareOrPublish({
                     tr: tr,
                     remainder: result.remainder});
             }
         }
     }
 
     if (location.hash) { /* TODO: dan: use this to replace the code block above
                             when new diffs are ready */
         var result = splitDelimitedHash(location.hash);
         var loc  = result.loc;
         if (loc.length > 1) {
+
+            var highlightable_line_tds = [];
+
+            // source code line format
             var page_highlights = loc.substring(
                 loc.indexOf('#') + 1).split('L');
 
             if (page_highlights.length > 1) {
                 var highlight_ranges = page_highlights[1].split(",");
                 var h_lines = [];
                 for (var pos in highlight_ranges) {
                     var _range = highlight_ranges[pos].split('-');
                     if (_range.length === 2) {
                         var start = parseInt(_range[0]);
                         var end = parseInt(_range[1]);
                         if (start < end) {
                             for (var i = start; i <= end; i++) {
                                 h_lines.push(i);
                             }
                         }
                     }
                     else {
                         h_lines.push(parseInt(highlight_ranges[pos]));
                     }
                 }
                 for (pos in h_lines) {
                     var line_td = $('td.cb-lineno#L' + h_lines[pos]);
                     if (line_td.length) {
-                        line_td.addClass('cb-line-selected'); // line number td
-                        line_td.next().addClass('cb-line-selected'); // line content
+                        highlightable_line_tds.push(line_td);
+                    }
                     }
                 }
-                var first_line_td = $('td.cb-lineno#L' + h_lines[0]);
-                if (first_line_td.length) {
-                    var elOffset = first_line_td.offset().top;
-                    var elHeight = first_line_td.height();
-                    var windowHeight = $(window).height();
-                    var offset;
 
-                    if (elHeight < windowHeight) {
-                        offset = elOffset - ((windowHeight / 4) - (elHeight / 2));
+            // now check a direct id reference (diff page)
+            if ($(loc).length && $(loc).hasClass('cb-lineno')) {
+                highlightable_line_tds.push($(loc));
                     }
-                    else {
-                        offset = elOffset;
-                    }
-                    $(function() { // let browser scroll to hash first, then
-                                   // scroll the line to the middle of page
-                        setTimeout(function() {
-                            $('html, body').animate({ scrollTop: offset });
-                          }, 100);
+            $.each(highlightable_line_tds, function (i, $td) {
+                $td.addClass('cb-line-selected'); // line number td
+                $td.next().addClass('cb-line-selected'); // line content
                     });
+
+            if (highlightable_line_tds.length) {
+                var $first_line_td = highlightable_line_tds[0];
+                scrollToElement($first_line_td);
                     $.Topic('/ui/plugins/code/anchor_focus').prepareOrPublish({
-                        lineno: first_line_td,
-                        remainder: result.remainder});
-                }
+                    lineno: $first_line_td,
+                    remainder: result.remainder
+                });
             }
         }
     }
     collapsableContent();
 });

rhodecode/templates/compare/compare_diff.html

@@ -1,322 +1,258 b''
 ## -*- coding: utf-8 -*-
 <%inherit file="/base/base.html"/>
+<%namespace name="cbdiffs" file="/codeblocks/diffs.html"/>
 
 <%def name="title()">
     %if c.compare_home:
         ${_('%s Compare') % c.repo_name}
     %else:
         ${_('%s Compare') % c.repo_name} - ${'%s@%s' % (c.source_repo.repo_name, c.source_ref)} &gt; ${'%s@%s' % (c.target_repo.repo_name, c.target_ref)}
     %endif
     %if c.rhodecode_name:
         &middot; ${h.branding(c.rhodecode_name)}
     %endif
 </%def>
 
 <%def name="breadcrumbs_links()">
   ${ungettext('%s commit','%s commits', len(c.commit_ranges)) % len(c.commit_ranges)}
 </%def>
 
 <%def name="menu_bar_nav()">
     ${self.menu_items(active='repositories')}
 </%def>
 
 <%def name="menu_bar_subnav()">
     ${self.repo_menu(active='compare')}
 </%def>
 
 <%def name="main()">
 <script type="text/javascript">
     // set fake commitId on this commit-range page
     templateContext.commit_data.commit_id = "${h.EmptyCommit().raw_id}";
 </script>
 
     <div class="box">
         <div class="title">
             ${self.repo_page_title(c.rhodecode_db_repo)}
             <div class="breadcrumbs">
                 ${_('Compare Commits')}
             </div>
         </div>
 
         <div class="table">
             <div id="codeblock" class="diffblock">
                 <div class="code-header" >
                     <div class="compare_header">
                         ## The hidden elements are replaced with a select2 widget
                         <div class="compare-label">${_('Target')}</div>${h.hidden('compare_source')}
                         <div class="compare-label">${_('Source')}</div>${h.hidden('compare_target')}
 
                         %if not c.preview_mode:
                             <div class="compare-label"></div>
                             <div class="compare-buttons">
                                 %if not c.compare_home:
                                     <a id="btn-swap" class="btn btn-primary" href="${c.swap_url}"><i class="icon-refresh"></i> ${_('Swap')}</a>
                                 %endif
                                 <div id="compare_revs" class="btn btn-primary"><i class ="icon-loop"></i> ${_('Compare Commits')}</div>
-                                %if c.files:
+                                %if c.diffset and c.diffset.files:
                                     <div id="compare_changeset_status_toggle" class="btn btn-primary">${_('Comment')}</div>
                                 %endif
                             </div>
                         %endif
                     </div>
                 </div>
             </div>
             ## use JS script to load it quickly before potentially large diffs render long time
             ## this prevents from situation when large diffs block rendering of select2 fields
             <script type="text/javascript">
 
                 var cache = {};
 
                 var formatSelection = function(repoName){
                     return function(data, container, escapeMarkup) {
                         var selection = data ? this.text(data) : "";
                         return escapeMarkup('{0}@{1}'.format(repoName, selection));
                     }
                 };
 
                 var feedCompareData = function(query, cachedValue){
                     var data = {results: []};
                     //filter results
                     $.each(cachedValue.results, function() {
                         var section = this.text;
                         var children = [];
                         $.each(this.children, function() {
                             if (query.term.length === 0 || this.text.toUpperCase().indexOf(query.term.toUpperCase()) >= 0) {
                                 children.push({
                                     'id': this.id,
                                     'text': this.text,
                                     'type': this.type
                                 })
                             }
                         });
                         data.results.push({
                             'text': section,
                             'children': children
                         })
                     });
                     //push the typed in changeset
                     data.results.push({
                         'text': _gettext('specify commit'),
                         'children': [{
                             'id': query.term,
                             'text': query.term,
                             'type': 'rev'
                         }]
                     });
                     query.callback(data);
                 };
 
                 var loadCompareData = function(repoName, query, cache){
                     $.ajax({
                         url: pyroutes.url('repo_refs_data', {'repo_name': repoName}),
                         data: {},
                         dataType: 'json',
                         type: 'GET',
                         success: function(data) {
                             cache[repoName] = data;
                             query.callback({results: data.results});
                         }
                     })
                 };
 
                 var enable_fields = ${"false" if c.preview_mode else "true"};
                 $("#compare_source").select2({
                     placeholder: "${'%s@%s' % (c.source_repo.repo_name, c.source_ref)}",
                     containerCssClass: "drop-menu",
                     dropdownCssClass: "drop-menu-dropdown",
                     formatSelection: formatSelection("${c.source_repo.repo_name}"),
                     dropdownAutoWidth: true,
                     query: function(query) {
                         var repoName = '${c.source_repo.repo_name}';
                         var cachedValue = cache[repoName];
 
                         if (cachedValue){
                             feedCompareData(query, cachedValue);
                         }
                         else {
                             loadCompareData(repoName, query, cache);
                         }
                     }
                 }).select2("enable", enable_fields);
 
                 $("#compare_target").select2({
                     placeholder: "${'%s@%s' % (c.target_repo.repo_name, c.target_ref)}",
                     dropdownAutoWidth: true,
                     containerCssClass: "drop-menu",
                     dropdownCssClass: "drop-menu-dropdown",
                     formatSelection: formatSelection("${c.target_repo.repo_name}"),
                     query: function(query) {
                         var repoName = '${c.target_repo.repo_name}';
                         var cachedValue = cache[repoName];
 
                         if (cachedValue){
                             feedCompareData(query, cachedValue);
                         }
                         else {
                             loadCompareData(repoName, query, cache);
                         }
                     }
                 }).select2("enable", enable_fields);
                 var initial_compare_source = {id: "${c.source_ref}", type:"${c.source_ref_type}"};
                 var initial_compare_target = {id: "${c.target_ref}", type:"${c.target_ref_type}"};
 
                 $('#compare_revs').on('click', function(e) {
                     var source = $('#compare_source').select2('data') || initial_compare_source;
                     var target = $('#compare_target').select2('data')  || initial_compare_target;
                     if (source && target) {
                         var url_data = {
                             repo_name: "${c.repo_name}",
                             source_ref: source.id,
                             source_ref_type: source.type,
                             target_ref: target.id,
                             target_ref_type: target.type
                         };
                         window.location = pyroutes.url('compare_url', url_data);
                     }
                 });
                 $('#compare_changeset_status_toggle').on('click', function(e) {
                     $('#compare_changeset_status').toggle();
                 });
 
             </script>
 
             ## changeset status form
             <%namespace name="comment" file="/changeset/changeset_file_comment.html"/>
             ## main comment form and it status
             <%
             def revs(_revs):
                 form_inputs = []
                 for cs in _revs:
                     tmpl = '<input type="hidden" data-commit-id="%(cid)s" name="commit_ids" value="%(cid)s">' % {'cid': cs.raw_id}
                     form_inputs.append(tmpl)
                 return form_inputs
             %>
             <div id="compare_changeset_status" style="display: none;">
                 ${comment.comments(h.url('changeset_comment', repo_name=c.repo_name, revision='0'*16), None, is_compare=True, form_extras=revs(c.commit_ranges))}
                 <script type="text/javascript">
 
                     mainCommentForm.setHandleFormSubmit(function(o) {
                         var text = mainCommentForm.cm.getValue();
                         var status = mainCommentForm.getCommentStatus();
 
                         if (text === "" && !status) {
                             return;
                         }
 
                         // we can pick which commits we want to make the comment by
                         // selecting them via click on preview pane, this will alter the hidden inputs
                         var cherryPicked = $('#changeset_compare_view_content .compare_select.hl').length > 0;
 
                         var commitIds = [];
                         $('#changeset_compare_view_content .compare_select').each(function(el) {
                             var commitId = this.id.replace('row-', '');
                             if ($(this).hasClass('hl') || !cherryPicked) {
                                 $("input[data-commit-id='{0}']".format(commitId)).val(commitId)
                                 commitIds.push(commitId);
                             } else {
                                 $("input[data-commit-id='{0}']".format(commitId)).val('')
                             }
                         });
 
                         mainCommentForm.setActionButtonsDisabled(true);
                         mainCommentForm.cm.setOption("readOnly", true);
                         var postData = {
                             'text': text,
                             'changeset_status': status,
                             'commit_ids': commitIds,
                             'csrf_token': CSRF_TOKEN
                         };
 
                         var submitSuccessCallback = function(o) {
                             location.reload(true);
                         };
                         var submitFailCallback = function(){
                             mainCommentForm.resetCommentFormState(text)
                         };
                         mainCommentForm.submitAjaxPOST(
                             mainCommentForm.submitUrl, postData, submitSuccessCallback, submitFailCallback);
                     });
                 </script>
 
             </div>
 
             %if c.compare_home:
                 <div id="changeset_compare_view_content">
                  <div class="help-block">${_('Compare commits, branches, bookmarks or tags.')}</div>
                 </div>
             %else:
                 <div id="changeset_compare_view_content">
                     ##CS
                     <%include file="compare_commits.html"/>
-
-                    ## FILES
-                  <div class="cs_files_title">
-                    <span class="cs_files_expand">
-                        <span id="expand_all_files">${_('Expand All')}</span> | <span id="collapse_all_files">${_('Collapse All')}</span>
-                    </span>
-                    <h2>
-                        ${diff_block.diff_summary_text(len(c.files), c.lines_added, c.lines_deleted, c.limited_diff)}
-                    </h2>
-                  </div>
-                    <div class="cs_files">
-                      %if not c.files:
-                         <p class="empty_data">${_('No files')}</p>
-                      %endif
-                  <table class="compare_view_files">
-                  <%namespace name="diff_block" file="/changeset/diff_block.html"/>
-                    %for FID, change, path, stats, file in c.files:
-                    <tr class="cs_${change} collapse_file" fid="${FID}">
-                        <td class="cs_icon_td">
-                            <span class="collapse_file_icon" fid="${FID}"></span>
-                        </td>
-                        <td class="cs_icon_td">
-                            <div class="flag_status not_reviewed hidden"></div>
-                        </td>
-                        <td class="cs_${change}" id="a_${FID}">
-                            <div class="node">
-                                <a href="#a_${FID}">
-                                    <i class="icon-file-${change.lower()}"></i>
-                                    ${h.safe_unicode(path)}
-                                </a>
-                            </div>
-                        </td>
-                        <td>
-                            <div class="changes pull-right">${h.fancy_file_stats(stats)}</div>
-                            <div class="comment-bubble pull-right" data-path="${path}">
-                              <i class="icon-comment"></i>
-                            </div>
-                        </td>
-                    </tr>
-                    <tr fid="${FID}" id="diff_${FID}" class="diff_links">
-                        <td></td>
-                        <td></td>
-                        <td class="cs_${change}">
-                            %if c.target_repo.repo_name == c.repo_name:
-                                ${diff_block.diff_menu(c.repo_name, h.safe_unicode(path), c.source_ref, c.target_ref, change, file)}
-                            %else:
-                                ## this is slightly different case later, since the target repo can have this
-                                ## file in target state than the source repo
-                                ${diff_block.diff_menu(c.target_repo.repo_name, h.safe_unicode(path), c.source_ref, c.target_ref, change, file)}
-                            %endif
-                        </td>
-                        <td class="td-actions rc-form">
-                        </td>
-                    </tr>
-                    <tr id="tr_${FID}">
-                      <td></td>
-                      <td></td>
-                      <td class="injected_diff" colspan="2">
-                          ${diff_block.diff_block_simple([c.changes[FID]])}
-                      </td>
-                    </tr>
-                  %endfor
-                  </table>
-                    % if c.limited_diff:
-                        ${diff_block.changeset_message()}
-                    % endif
+                    ${cbdiffs.render_diffset(c.diffset)}
                  </div>
             %endif
         </div>
     </div>
 </div>
 </%def>

rhodecode/tests/functional/test_changeset.py

@@ -1,286 +1,299 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2010-2016  RhodeCode GmbH
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License, version 3
 # (only), as published by the Free Software Foundation.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # This program is dual-licensed. If you wish to learn more about the
 # RhodeCode Enterprise Edition, including its added features, Support services,
 # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 import pytest
 
 from rhodecode.lib.helpers import _shorten_commit_id
 from rhodecode.tests import url
 
 
 @pytest.mark.usefixtures("app")
 class TestChangesetController(object):
 
     def test_index(self, backend):
         commit_id = self.commit_id[backend.alias]
         response = self.app.get(url(
             controller='changeset', action='index',
             repo_name=backend.repo_name, revision=commit_id))
         response.mustcontain('Added a symlink')
         response.mustcontain(commit_id)
         response.mustcontain('No newline at end of file')
 
     def test_index_raw(self, backend):
         commit_id = self.commit_id[backend.alias]
         response = self.app.get(url(
             controller='changeset', action='changeset_raw',
             repo_name=backend.repo_name, revision=commit_id))
         assert response.body == self.diffs[backend.alias]
 
     def test_index_raw_patch(self, backend):
         response = self.app.get(url(
             controller='changeset', action='changeset_patch',
             repo_name=backend.repo_name,
             revision=self.commit_id[backend.alias]))
         assert response.body == self.patches[backend.alias]
 
     def test_index_changeset_download(self, backend):
         response = self.app.get(url(
             controller='changeset', action='changeset_download',
             repo_name=backend.repo_name,
             revision=self.commit_id[backend.alias]))
         assert response.body == self.diffs[backend.alias]
 
     def test_single_commit_page_different_ops(self, backend):
         commit_id = {
             'hg': '603d6c72c46d953420c89d36372f08d9f305f5dd',
             'git': '03fa803d7e9fb14daa9a3089e0d1494eda75d986',
             'svn': '337',
         }
         commit_id = commit_id[backend.alias]
         response = self.app.get(url(
             controller='changeset', action='index',
             repo_name=backend.repo_name, revision=commit_id))
 
         response.mustcontain(_shorten_commit_id(commit_id))
         response.mustcontain('21 files changed: 943 inserted, 288 deleted')
 
         # files op files
         response.mustcontain('File no longer present at commit: %s' %
                              _shorten_commit_id(commit_id))
 
         # svn uses a different filename
         if backend.alias == 'svn':
             response.mustcontain('new file 10644')
         else:
             response.mustcontain('new file 100644')
         response.mustcontain('Changed theme to ADC theme')  # commit msg
 
         self._check_diff_menus(response, right_menu=True)
 
     def test_commit_range_page_different_ops(self, backend):
         commit_id_range = {
             'hg': (
                 '25d7e49c18b159446cadfa506a5cf8ad1cb04067',
                 '603d6c72c46d953420c89d36372f08d9f305f5dd'),
             'git': (
                 '6fc9270775aaf5544c1deb014f4ddd60c952fcbb',
                 '03fa803d7e9fb14daa9a3089e0d1494eda75d986'),
             'svn': (
                 '335',
                 '337'),
         }
         commit_ids = commit_id_range[backend.alias]
         commit_id = '%s...%s' % (commit_ids[0], commit_ids[1])
         response = self.app.get(url(
             controller='changeset', action='index',
             repo_name=backend.repo_name, revision=commit_id))
 
         response.mustcontain(_shorten_commit_id(commit_ids[0]))
         response.mustcontain(_shorten_commit_id(commit_ids[1]))
         
         # svn is special
         if backend.alias == 'svn':
             response.mustcontain('new file 10644')
             response.mustcontain('34 files changed: 1184 inserted, 311 deleted')
         else:
             response.mustcontain('new file 100644')
             response.mustcontain('33 files changed: 1165 inserted, 308 deleted')
 
         # files op files
         response.mustcontain('File no longer present at commit: %s' %
                              _shorten_commit_id(commit_ids[1]))
         response.mustcontain('Added docstrings to vcs.cli')  # commit msg
         response.mustcontain('Changed theme to ADC theme')  # commit msg
 
         self._check_diff_menus(response)
 
     def test_combined_compare_commit_page_different_ops(self, backend):
         commit_id_range = {
             'hg': (
                 '4fdd71e9427417b2e904e0464c634fdee85ec5a7',
                 '603d6c72c46d953420c89d36372f08d9f305f5dd'),
             'git': (
                 'f5fbf9cfd5f1f1be146f6d3b38bcd791a7480c13',
                 '03fa803d7e9fb14daa9a3089e0d1494eda75d986'),
             'svn': (
                 '335',
                 '337'),
         }
         commit_ids = commit_id_range[backend.alias]
         response = self.app.get(url(
             controller='compare', action='compare',
             repo_name=backend.repo_name,
             source_ref_type='rev', source_ref=commit_ids[0],
             target_ref_type='rev', target_ref=commit_ids[1], ))
 
         response.mustcontain(_shorten_commit_id(commit_ids[0]))
         response.mustcontain(_shorten_commit_id(commit_ids[1]))
 
         # files op files
         response.mustcontain('File no longer present at commit: %s' %
                              _shorten_commit_id(commit_ids[1]))
         
         # svn is special
         if backend.alias == 'svn':
             response.mustcontain('new file 10644')
             response.mustcontain('32 files changed: 1179 inserted, 310 deleted')
         else:
             response.mustcontain('new file 100644')
             response.mustcontain('32 files changed: 1165 inserted, 308 deleted')
 
         response.mustcontain('Added docstrings to vcs.cli')  # commit msg
         response.mustcontain('Changed theme to ADC theme')  # commit msg
 
-        self._check_diff_menus(response)
+        self._check_new_diff_menus(response)
 
     def test_changeset_range(self, backend):
         self._check_changeset_range(
             backend, self.commit_id_range, self.commit_id_range_result)
 
     def test_changeset_range_with_initial_commit(self, backend):
         commit_id_range = {
             'hg': (
                 'b986218ba1c9b0d6a259fac9b050b1724ed8e545'
                 '...6cba7170863a2411822803fa77a0a264f1310b35'),
             'git': (
                 'c1214f7e79e02fc37156ff215cd71275450cffc3'
                 '...fa6600f6848800641328adbf7811fd2372c02ab2'),
             'svn': '1...3',
         }
         commit_id_range_result = {
             'hg': ['b986218ba1c9', '3d8f361e72ab', '6cba7170863a'],
             'git': ['c1214f7e79e0', '38b5fe81f109', 'fa6600f68488'],
             'svn': ['1', '2', '3'],
         }
         self._check_changeset_range(
             backend, commit_id_range, commit_id_range_result)
 
     def _check_changeset_range(
             self, backend, commit_id_ranges, commit_id_range_result):
         response = self.app.get(
             url(controller='changeset', action='index',
                 repo_name=backend.repo_name,
                 revision=commit_id_ranges[backend.alias]))
         expected_result = commit_id_range_result[backend.alias]
         response.mustcontain('{} commits'.format(len(expected_result)))
         for commit_id in expected_result:
             response.mustcontain(commit_id)
 
     commit_id = {
         'hg': '2062ec7beeeaf9f44a1c25c41479565040b930b2',
         'svn': '393',
         'git': 'fd627b9e0dd80b47be81af07c4a98518244ed2f7',
     }
 
     commit_id_range = {
         'hg': (
             'a53d9201d4bc278910d416d94941b7ea007ecd52'
             '...2062ec7beeeaf9f44a1c25c41479565040b930b2'),
         'git': (
             '7ab37bc680b4aa72c34d07b230c866c28e9fc204'
             '...fd627b9e0dd80b47be81af07c4a98518244ed2f7'),
         'svn': '391...393',
     }
 
     commit_id_range_result = {
         'hg': ['a53d9201d4bc', '96507bd11ecc', '2062ec7beeea'],
         'git': ['7ab37bc680b4', '5f2c6ee19592', 'fd627b9e0dd8'],
         'svn': ['391', '392', '393'],
     }
 
     diffs = {
         'hg': r"""diff --git a/README b/README
 new file mode 120000
 --- /dev/null
 +++ b/README
 @@ -0,0 +1,1 @@
 +README.rst
 \ No newline at end of file
 """,
         'git': r"""diff --git a/README b/README
 new file mode 120000
 index 0000000000000000000000000000000000000000..92cacd285355271487b7e379dba6ca60f9a554a4
 --- /dev/null
 +++ b/README
 @@ -0,0 +1 @@
 +README.rst
 \ No newline at end of file
 """,
         'svn': """Index: README
 ===================================================================
 diff --git a/README b/README
 new file mode 10644
 --- /dev/null\t(revision 0)
 +++ b/README\t(revision 393)
 @@ -0,0 +1 @@
 +link README.rst
 \\ No newline at end of file
 """,
     }
 
     patches = {
         'hg': r"""# HG changeset patch
 # User Marcin Kuzminski <[e-mail]>
 # Date 2014-01-07 12:21:40
 # Node ID 2062ec7beeeaf9f44a1c25c41479565040b930b2
 # Parent  96507bd11ecc815ebc6270fdf6db110928c09c1e
 
 Added a symlink
 
 """ + diffs['hg'],
         'git': r"""From fd627b9e0dd80b47be81af07c4a98518244ed2f7 2014-01-07 12:22:20
 From: Marcin Kuzminski <[e-mail]>
 Date: 2014-01-07 12:22:20
 Subject: [PATCH] Added a symlink
 
 ---
 
 """ + diffs['git'],
         'svn': r"""# SVN changeset patch
 # User marcin
 # Date 2014-09-02 12:25:22.071142
 # Revision 393
 
 Added a symlink
 
 """ + diffs['svn'],
     }
 
-    def _check_diff_menus(self, response, right_menu=False):
+    def _check_diff_menus(self, response, right_menu=False,):
         # diff menus
         for elem in ['Show File', 'Unified Diff', 'Side-by-side Diff',
                      'Raw Diff', 'Download Diff']:
             response.mustcontain(elem)
 
         # right pane diff menus
         if right_menu:
             for elem in ['Ignore whitespace', 'Increase context',
                          'Hide comments']:
                 response.mustcontain(elem)
+
+
+    def _check_new_diff_menus(self, response, right_menu=False,):
+        # diff menus
+        for elem in ['Show file before', 'Show file after',
+                     'Raw diff', 'Download diff']:
+            response.mustcontain(elem)
+
+        # right pane diff menus
+        if right_menu:
+            for elem in ['Ignore whitespace', 'Increase context',
+                         'Hide comments']:
+                response.mustcontain(elem)

rhodecode/tests/functional/test_compare.py

@@ -1,691 +1,695 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2010-2016  RhodeCode GmbH
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License, version 3
 # (only), as published by the Free Software Foundation.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # This program is dual-licensed. If you wish to learn more about the
 # RhodeCode Enterprise Edition, including its added features, Support services,
 # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 import mock
 import pytest
+import lxml.html
 
 from rhodecode.lib.vcs.backends.base import EmptyCommit
 from rhodecode.lib.vcs.exceptions import RepositoryRequirementError
 from rhodecode.model.db import Repository
 from rhodecode.model.scm import ScmModel
 from rhodecode.tests import url, TEST_USER_ADMIN_LOGIN, assert_session_flash
 from rhodecode.tests.utils import AssertResponse
 
 
 @pytest.mark.usefixtures("autologin_user", "app")
 class TestCompareController:
 
     @pytest.mark.xfail_backends("svn", reason="Requires pull")
     def test_compare_remote_with_different_commit_indexes(self, backend):
         # Preparing the following repository structure:
         #
         # Origin repository has two commits:
         #
         #    0    1
         #    A -- D
         #
         # The fork of it has a few more commits and "D" has a commit index
         # which does not exist in origin.
         #
         #    0    1    2    3    4
         #    A --   --   -- D -- E
         #      \- B -- C
         #
 
         fork = backend.create_repo()
 
         # prepare fork
         commit0 = _commit_change(
             fork.repo_name, filename='file1', content='A',
             message='A', vcs_type=backend.alias, parent=None, newfile=True)
 
         commit1 = _commit_change(
             fork.repo_name, filename='file1', content='B',
             message='B, child of A', vcs_type=backend.alias, parent=commit0)
 
         _commit_change(  # commit 2
             fork.repo_name, filename='file1', content='C',
             message='C, child of B', vcs_type=backend.alias, parent=commit1)
 
         commit3 = _commit_change(
             fork.repo_name, filename='file1', content='D',
             message='D, child of A', vcs_type=backend.alias, parent=commit0)
 
         commit4 = _commit_change(
             fork.repo_name, filename='file1', content='E',
             message='E, child of D', vcs_type=backend.alias, parent=commit3)
 
         # prepare origin repository, taking just the history up to D
         origin = backend.create_repo()
 
         origin_repo = origin.scm_instance(cache=False)
         origin_repo.config.clear_section('hooks')
         origin_repo.pull(fork.repo_full_path, commit_ids=[commit3.raw_id])
 
         # Verify test fixture setup
         # This does not work for git
         if backend.alias != 'git':
             assert 5 == len(fork.scm_instance().commit_ids)
             assert 2 == len(origin_repo.commit_ids)
 
         # Comparing the revisions
         response = self.app.get(
             url('compare_url',
                 repo_name=origin.repo_name,
                 source_ref_type="rev",
                 source_ref=commit3.raw_id,
                 target_repo=fork.repo_name,
                 target_ref_type="rev",
                 target_ref=commit4.raw_id,
                 merge='1',))
 
         compare_page = ComparePage(response)
         compare_page.contains_commits([commit4])
 
     @pytest.mark.xfail_backends("svn", reason="Depends on branch support")
     def test_compare_forks_on_branch_extra_commits(self, backend):
         repo1 = backend.create_repo()
 
         # commit something !
         commit0 = _commit_change(
             repo1.repo_name, filename='file1', content='line1\n',
             message='commit1', vcs_type=backend.alias, parent=None,
             newfile=True)
 
         # fork this repo
         repo2 = backend.create_fork()
 
         # add two extra commit into fork
         commit1 = _commit_change(
             repo2.repo_name, filename='file1', content='line1\nline2\n',
             message='commit2', vcs_type=backend.alias, parent=commit0)
 
         commit2 = _commit_change(
             repo2.repo_name, filename='file1', content='line1\nline2\nline3\n',
             message='commit3', vcs_type=backend.alias, parent=commit1)
 
         commit_id1 = repo1.scm_instance().DEFAULT_BRANCH_NAME
         commit_id2 = repo2.scm_instance().DEFAULT_BRANCH_NAME
 
         response = self.app.get(
             url('compare_url',
                 repo_name=repo1.repo_name,
                 source_ref_type="branch",
                 source_ref=commit_id2,
                 target_repo=repo2.repo_name,
                 target_ref_type="branch",
                 target_ref=commit_id1,
                 merge='1',))
 
         response.mustcontain('%s@%s' % (repo1.repo_name, commit_id2))
         response.mustcontain('%s@%s' % (repo2.repo_name, commit_id1))
 
         compare_page = ComparePage(response)
         compare_page.contains_change_summary(1, 2, 0)
         compare_page.contains_commits([commit1, commit2])
         compare_page.contains_file_links_and_anchors([
             ('file1', 'a_c--826e8142e6ba'),
         ])
 
         # Swap is removed when comparing branches since it's a PR feature and
         # it is then a preview mode
         compare_page.swap_is_hidden()
         compare_page.target_source_are_disabled()
 
     @pytest.mark.xfail_backends("svn", reason="Depends on branch support")
     def test_compare_forks_on_branch_extra_commits_origin_has_incomming(
             self, backend):
         repo1 = backend.create_repo()
 
         # commit something !
         commit0 = _commit_change(
             repo1.repo_name, filename='file1', content='line1\n',
             message='commit1', vcs_type=backend.alias, parent=None,
             newfile=True)
 
         # fork this repo
         repo2 = backend.create_fork()
 
         # now commit something to origin repo
         _commit_change(
             repo1.repo_name, filename='file2', content='line1file2\n',
             message='commit2', vcs_type=backend.alias, parent=commit0,
             newfile=True)
 
         # add two extra commit into fork
         commit1 = _commit_change(
             repo2.repo_name, filename='file1', content='line1\nline2\n',
             message='commit2', vcs_type=backend.alias, parent=commit0)
 
         commit2 = _commit_change(
             repo2.repo_name, filename='file1', content='line1\nline2\nline3\n',
             message='commit3', vcs_type=backend.alias, parent=commit1)
 
         commit_id1 = repo1.scm_instance().DEFAULT_BRANCH_NAME
         commit_id2 = repo2.scm_instance().DEFAULT_BRANCH_NAME
 
         response = self.app.get(
             url('compare_url',
                 repo_name=repo1.repo_name,
                 source_ref_type="branch",
                 source_ref=commit_id2,
                 target_repo=repo2.repo_name,
                 target_ref_type="branch",
                 target_ref=commit_id1,
                 merge='1'))
 
         response.mustcontain('%s@%s' % (repo1.repo_name, commit_id2))
         response.mustcontain('%s@%s' % (repo2.repo_name, commit_id1))
 
         compare_page = ComparePage(response)
         compare_page.contains_change_summary(1, 2, 0)
         compare_page.contains_commits([commit1, commit2])
         compare_page.contains_file_links_and_anchors([
             ('file1', 'a_c--826e8142e6ba'),
         ])
 
         # Swap is removed when comparing branches since it's a PR feature and
         # it is then a preview mode
         compare_page.swap_is_hidden()
         compare_page.target_source_are_disabled()
 
     @pytest.mark.xfail_backends("svn", "git")
     def test_compare_of_unrelated_forks(self, backend):
         # TODO: johbo: Fails for git due to some other issue it seems
         orig = backend.create_repo(number_of_commits=1)
         fork = backend.create_repo(number_of_commits=1)
 
         response = self.app.get(
             url('compare_url',
                 repo_name=orig.repo_name,
                 action="compare",
                 source_ref_type="rev",
                 source_ref="tip",
                 target_ref_type="rev",
                 target_ref="tip",
                 merge='1',
                 target_repo=fork.repo_name),
             status=400)
 
         response.mustcontain("Repositories unrelated.")
 
     @pytest.mark.xfail_backends("svn")
     def test_compare_cherry_pick_commits_from_bottom(self, backend):
 
         # repo1:
         #     commit0:
         #     commit1:
         # repo1-fork- in which we will cherry pick bottom commits
         #     commit0:
         #     commit1:
         #     commit2: x
         #     commit3: x
         #     commit4: x
         #     commit5:
         # make repo1, and commit1+commit2
 
         repo1 = backend.create_repo()
 
         # commit something !
         commit0 = _commit_change(
             repo1.repo_name, filename='file1', content='line1\n',
             message='commit1', vcs_type=backend.alias, parent=None,
             newfile=True)
         commit1 = _commit_change(
             repo1.repo_name, filename='file1', content='line1\nline2\n',
             message='commit2', vcs_type=backend.alias, parent=commit0)
 
         # fork this repo
         repo2 = backend.create_fork()
 
         # now make commit3-6
         commit2 = _commit_change(
             repo1.repo_name, filename='file1', content='line1\nline2\nline3\n',
             message='commit3', vcs_type=backend.alias, parent=commit1)
         commit3 = _commit_change(
             repo1.repo_name, filename='file1',
             content='line1\nline2\nline3\nline4\n', message='commit4',
             vcs_type=backend.alias, parent=commit2)
         commit4 = _commit_change(
             repo1.repo_name, filename='file1',
             content='line1\nline2\nline3\nline4\nline5\n', message='commit5',
             vcs_type=backend.alias, parent=commit3)
         _commit_change(  # commit 5
             repo1.repo_name, filename='file1',
             content='line1\nline2\nline3\nline4\nline5\nline6\n',
             message='commit6', vcs_type=backend.alias, parent=commit4)
 
         response = self.app.get(
             url('compare_url',
                 repo_name=repo2.repo_name,
                 source_ref_type="rev",
                 # parent of commit2, in target repo2
                 source_ref=commit1.raw_id,
                 target_repo=repo1.repo_name,
                 target_ref_type="rev",
                 target_ref=commit4.raw_id,
                 merge='1',))
         response.mustcontain('%s@%s' % (repo2.repo_name, commit1.short_id))
         response.mustcontain('%s@%s' % (repo1.repo_name, commit4.short_id))
 
         # files
         compare_page = ComparePage(response)
         compare_page.contains_change_summary(1, 3, 0)
         compare_page.contains_commits([commit2, commit3, commit4])
         compare_page.contains_file_links_and_anchors([
             ('file1', 'a_c--826e8142e6ba'),
         ])
 
     @pytest.mark.xfail_backends("svn")
     def test_compare_cherry_pick_commits_from_top(self, backend):
         # repo1:
         #     commit0:
         #     commit1:
         # repo1-fork- in which we will cherry pick bottom commits
         #     commit0:
         #     commit1:
         #     commit2:
         #     commit3: x
         #     commit4: x
         #     commit5: x
 
         # make repo1, and commit1+commit2
         repo1 = backend.create_repo()
 
         # commit something !
         commit0 = _commit_change(
             repo1.repo_name, filename='file1', content='line1\n',
             message='commit1', vcs_type=backend.alias, parent=None,
             newfile=True)
         commit1 = _commit_change(
             repo1.repo_name, filename='file1', content='line1\nline2\n',
             message='commit2', vcs_type=backend.alias, parent=commit0)
 
         # fork this repo
         backend.create_fork()
 
         # now make commit3-6
         commit2 = _commit_change(
             repo1.repo_name, filename='file1', content='line1\nline2\nline3\n',
             message='commit3', vcs_type=backend.alias, parent=commit1)
         commit3 = _commit_change(
             repo1.repo_name, filename='file1',
             content='line1\nline2\nline3\nline4\n', message='commit4',
             vcs_type=backend.alias, parent=commit2)
         commit4 = _commit_change(
             repo1.repo_name, filename='file1',
             content='line1\nline2\nline3\nline4\nline5\n', message='commit5',
             vcs_type=backend.alias, parent=commit3)
         commit5 = _commit_change(
             repo1.repo_name, filename='file1',
             content='line1\nline2\nline3\nline4\nline5\nline6\n',
             message='commit6', vcs_type=backend.alias, parent=commit4)
 
         response = self.app.get(
             url('compare_url',
                 repo_name=repo1.repo_name,
                 source_ref_type="rev",
                 # parent of commit3, not in source repo2
                 source_ref=commit2.raw_id,
                 target_ref_type="rev",
                 target_ref=commit5.raw_id,
                 merge='1',))
 
         response.mustcontain('%s@%s' % (repo1.repo_name, commit2.short_id))
         response.mustcontain('%s@%s' % (repo1.repo_name, commit5.short_id))
 
         compare_page = ComparePage(response)
         compare_page.contains_change_summary(1, 3, 0)
         compare_page.contains_commits([commit3, commit4, commit5])
 
         # files
         compare_page.contains_file_links_and_anchors([
             ('file1', 'a_c--826e8142e6ba'),
         ])
 
     @pytest.mark.xfail_backends("svn")
     def test_compare_remote_branches(self, backend):
         repo1 = backend.repo
         repo2 = backend.create_fork()
 
         commit_id1 = repo1.get_commit(commit_idx=3).raw_id
         commit_id2 = repo1.get_commit(commit_idx=6).raw_id
 
         response = self.app.get(
             url('compare_url',
                 repo_name=repo1.repo_name,
                 source_ref_type="rev",
                 source_ref=commit_id1,
                 target_ref_type="rev",
                 target_ref=commit_id2,
                 target_repo=repo2.repo_name,
                 merge='1',))
 
         response.mustcontain('%s@%s' % (repo1.repo_name, commit_id1))
         response.mustcontain('%s@%s' % (repo2.repo_name, commit_id2))
 
         compare_page = ComparePage(response)
 
         # outgoing commits between those commits
         compare_page.contains_commits(
             [repo2.get_commit(commit_idx=x) for x in [4, 5, 6]])
 
         # files
         compare_page.contains_file_links_and_anchors([
             ('vcs/backends/hg.py', 'a_c--9c390eb52cd6'),
             ('vcs/backends/__init__.py', 'a_c--41b41c1f2796'),
             ('vcs/backends/base.py', 'a_c--2f574d260608'),
         ])
 
     @pytest.mark.xfail_backends("svn")
     def test_source_repo_new_commits_after_forking_simple_diff(self, backend):
         repo1 = backend.create_repo()
         r1_name = repo1.repo_name
 
         commit0 = _commit_change(
             repo=r1_name, filename='file1',
             content='line1', message='commit1', vcs_type=backend.alias,
             newfile=True)
         assert repo1.scm_instance().commit_ids == [commit0.raw_id]
 
         # fork the repo1
         repo2 = backend.create_fork()
         assert repo2.scm_instance().commit_ids == [commit0.raw_id]
 
         self.r2_id = repo2.repo_id
         r2_name = repo2.repo_name
 
         commit1 = _commit_change(
             repo=r2_name, filename='file1-fork',
             content='file1-line1-from-fork', message='commit1-fork',
             vcs_type=backend.alias, parent=repo2.scm_instance()[-1],
             newfile=True)
 
         commit2 = _commit_change(
             repo=r2_name, filename='file2-fork',
             content='file2-line1-from-fork', message='commit2-fork',
             vcs_type=backend.alias, parent=commit1,
             newfile=True)
 
         _commit_change(  # commit 3
             repo=r2_name, filename='file3-fork',
             content='file3-line1-from-fork', message='commit3-fork',
             vcs_type=backend.alias, parent=commit2, newfile=True)
 
         # compare !
         commit_id1 = repo1.scm_instance().DEFAULT_BRANCH_NAME
         commit_id2 = repo2.scm_instance().DEFAULT_BRANCH_NAME
 
         response = self.app.get(
             url('compare_url',
                 repo_name=r2_name,
                 source_ref_type="branch",
                 source_ref=commit_id1,
                 target_ref_type="branch",
                 target_ref=commit_id2,
                 target_repo=r1_name,
                 merge='1',))
 
         response.mustcontain('%s@%s' % (r2_name, commit_id1))
         response.mustcontain('%s@%s' % (r1_name, commit_id2))
         response.mustcontain('No files')
         response.mustcontain('No Commits')
 
         commit0 = _commit_change(
             repo=r1_name, filename='file2',
             content='line1-added-after-fork', message='commit2-parent',
             vcs_type=backend.alias, parent=None, newfile=True)
 
         # compare !
         response = self.app.get(
             url('compare_url',
                 repo_name=r2_name,
                 source_ref_type="branch",
                 source_ref=commit_id1,
                 target_ref_type="branch",
                 target_ref=commit_id2,
                 target_repo=r1_name,
                 merge='1',))
 
         response.mustcontain('%s@%s' % (r2_name, commit_id1))
         response.mustcontain('%s@%s' % (r1_name, commit_id2))
 
         response.mustcontain("""commit2-parent""")
         response.mustcontain("""line1-added-after-fork""")
         compare_page = ComparePage(response)
         compare_page.contains_change_summary(1, 1, 0)
 
     @pytest.mark.xfail_backends("svn")
     def test_compare_commits(self, backend):
         commit0 = backend.repo.get_commit(commit_idx=0)
         commit1 = backend.repo.get_commit(commit_idx=1)
 
         response = self.app.get(
             url('compare_url',
                 repo_name=backend.repo_name,
                 source_ref_type="rev",
                 source_ref=commit0.raw_id,
                 target_ref_type="rev",
                 target_ref=commit1.raw_id,
                 merge='1',),
             extra_environ={'HTTP_X_PARTIAL_XHR': '1'},)
 
         # outgoing commits between those commits
         compare_page = ComparePage(response)
         compare_page.contains_commits(commits=[commit1], ancestors=[commit0])
 
     def test_errors_when_comparing_unknown_repo(self, backend):
         repo = backend.repo
         badrepo = 'badrepo'
 
         response = self.app.get(
             url('compare_url',
                 repo_name=repo.repo_name,
                 source_ref_type="rev",
                 source_ref='tip',
                 target_ref_type="rev",
                 target_ref='tip',
                 target_repo=badrepo,
                 merge='1',),
             status=302)
         redirected = response.follow()
         redirected.mustcontain('Could not find the other repo: %s' % badrepo)
 
     def test_compare_not_in_preview_mode(self, backend_stub):
         commit0 = backend_stub.repo.get_commit(commit_idx=0)
         commit1 = backend_stub.repo.get_commit(commit_idx=1)
 
         response = self.app.get(url('compare_url',
                                     repo_name=backend_stub.repo_name,
                                     source_ref_type="rev",
                                     source_ref=commit0.raw_id,
                                     target_ref_type="rev",
                                     target_ref=commit1.raw_id,
                                     ),)
 
         # outgoing commits between those commits
         compare_page = ComparePage(response)
         compare_page.swap_is_visible()
         compare_page.target_source_are_enabled()
 
     def test_compare_of_fork_with_largefiles(self, backend_hg, settings_util):
         orig = backend_hg.create_repo(number_of_commits=1)
         fork = backend_hg.create_fork()
 
         settings_util.create_repo_rhodecode_ui(
             orig, 'extensions', value='', key='largefiles', active=False)
         settings_util.create_repo_rhodecode_ui(
             fork, 'extensions', value='', key='largefiles', active=True)
 
         compare_module = ('rhodecode.lib.vcs.backends.hg.repository.'
                           'MercurialRepository.compare')
         with mock.patch(compare_module) as compare_mock:
             compare_mock.side_effect = RepositoryRequirementError()
 
             response = self.app.get(
                 url('compare_url',
                     repo_name=orig.repo_name,
                     action="compare",
                     source_ref_type="rev",
                     source_ref="tip",
                     target_ref_type="rev",
                     target_ref="tip",
                     merge='1',
                     target_repo=fork.repo_name),
                 status=302)
 
             assert_session_flash(
                 response,
                 'Could not compare repos with different large file settings')
 
 
 @pytest.mark.usefixtures("autologin_user")
 class TestCompareControllerSvn:
 
     def test_supports_references_with_path(self, app, backend_svn):
         repo = backend_svn['svn-simple-layout']
         commit_id = repo.get_commit(commit_idx=-1).raw_id
         response = app.get(
             url('compare_url',
                 repo_name=repo.repo_name,
                 source_ref_type="tag",
                 source_ref="%s@%s" % ('tags/v0.1', commit_id),
                 target_ref_type="tag",
                 target_ref="%s@%s" % ('tags/v0.2', commit_id),
                 merge='1',),
             status=200)
 
         # Expecting no commits, since both paths are at the same revision
         response.mustcontain('No Commits')
 
         # Should find only one file changed when comparing those two tags
         response.mustcontain('example.py')
         compare_page = ComparePage(response)
         compare_page.contains_change_summary(1, 5, 1)
 
     def test_shows_commits_if_different_ids(self, app, backend_svn):
         repo = backend_svn['svn-simple-layout']
         source_id = repo.get_commit(commit_idx=-6).raw_id
         target_id = repo.get_commit(commit_idx=-1).raw_id
         response = app.get(
             url('compare_url',
                 repo_name=repo.repo_name,
                 source_ref_type="tag",
                 source_ref="%s@%s" % ('tags/v0.1', source_id),
                 target_ref_type="tag",
                 target_ref="%s@%s" % ('tags/v0.2', target_id),
                 merge='1',),
             status=200)
 
         # It should show commits
         assert 'No Commits' not in response.body
 
         # Should find only one file changed when comparing those two tags
         response.mustcontain('example.py')
         compare_page = ComparePage(response)
         compare_page.contains_change_summary(1, 5, 1)
 
 
 class ComparePage(AssertResponse):
     """
     Abstracts the page template from the tests
     """
 
     def contains_file_links_and_anchors(self, files):
+        doc = lxml.html.fromstring(self.response.body)
         for filename, file_id in files:
-            self.contains_one_link(filename, '#' + file_id)
             self.contains_one_anchor(file_id)
+            diffblock = doc.cssselect('[data-f-path="%s"]' % filename)
+            assert len(diffblock) == 1
+            assert len(diffblock[0].cssselect('a[href="#%s"]' % file_id)) == 1
 
     def contains_change_summary(self, files_changed, inserted, deleted):
         template = (
             "{files_changed} file{plural} changed: "
             "{inserted} inserted, {deleted} deleted")
         self.response.mustcontain(template.format(
             files_changed=files_changed,
             plural="s" if files_changed > 1 else "",
             inserted=inserted,
             deleted=deleted))
 
     def contains_commits(self, commits, ancestors=None):
         response = self.response
 
         for commit in commits:
             # Expecting to see the commit message in an element which
             # has the ID "c-{commit.raw_id}"
             self.element_contains('#c-' + commit.raw_id, commit.message)
             self.contains_one_link(
                 'r%s:%s' % (commit.idx, commit.short_id),
                 self._commit_url(commit))
         if ancestors:
             response.mustcontain('Ancestor')
             for ancestor in ancestors:
                 self.contains_one_link(
                     ancestor.short_id, self._commit_url(ancestor))
 
     def _commit_url(self, commit):
         return '/%s/changeset/%s' % (commit.repository.name, commit.raw_id)
 
     def swap_is_hidden(self):
         assert '<a id="btn-swap"' not in self.response.text
 
     def swap_is_visible(self):
         assert '<a id="btn-swap"' in self.response.text
 
     def target_source_are_disabled(self):
         response = self.response
         response.mustcontain("var enable_fields = false;")
         response.mustcontain('.select2("enable", enable_fields)')
 
     def target_source_are_enabled(self):
         response = self.response
         response.mustcontain("var enable_fields = true;")
 
 
 def _commit_change(
         repo, filename, content, message, vcs_type, parent=None,
         newfile=False):
     repo = Repository.get_by_repo_name(repo)
     _commit = parent
     if not parent:
         _commit = EmptyCommit(alias=vcs_type)
 
     if newfile:
         nodes = {
             filename: {
                 'content': content
             }
         }
         commit = ScmModel().create_nodes(
             user=TEST_USER_ADMIN_LOGIN, repo=repo,
             message=message,
             nodes=nodes,
             parent_commit=_commit,
             author=TEST_USER_ADMIN_LOGIN,
         )
     else:
         commit = ScmModel().commit_change(
             repo=repo.scm_instance(), repo_name=repo.repo_name,
             commit=parent, user=TEST_USER_ADMIN_LOGIN,
             author=TEST_USER_ADMIN_LOGIN,
             message=message,
             content=content,
             f_path=filename
         )
     return commit

rhodecode/tests/lib/test_codeblocks.py

@@ -1,330 +1,330 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2016-2016  RhodeCode GmbH
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License, version 3
 # (only), as published by the Free Software Foundation.
 #
 # This program is distributed in the hope that it will be useful,
 # but WITHOUT ANY WARRANTY; without even the implied warranty of
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # This program is dual-licensed. If you wish to learn more about the
 # RhodeCode Enterprise Edition, including its added features, Support services,
 # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 import pytest
 
 from rhodecode.lib.codeblocks import (
     tokenize_string, split_token_stream, rollup_tokenstream,
     render_tokenstream)
 from pygments.lexers import get_lexer_by_name
 
 
 class TestTokenizeString(object):
 
     python_code = '''
     import this
 
     var = 6
     print "this"
 
     '''
 
     def test_tokenize_as_python(self):
         lexer = get_lexer_by_name('python')
         tokens = list(tokenize_string(self.python_code, lexer))
 
         assert tokens == [
             ('',    u'\n'),
             ('',    u'    '),
             ('kn',  u'import'),
             ('',    u' '),
             ('nn',  u'this'),
             ('',    u'\n'),
             ('',    u'\n'),
             ('',    u'    '),
             ('n',   u'var'),
             ('',    u' '),
             ('o',   u'='),
             ('',    u' '),
             ('mi',  u'6'),
             ('',    u'\n'),
             ('',    u'    '),
             ('k',   u'print'),
             ('',    u' '),
             ('s2',  u'"'),
             ('s2',  u'this'),
             ('s2',  u'"'),
             ('',    u'\n'),
             ('',    u'\n'),
             ('',    u'    ')
         ]
 
     def test_tokenize_as_text(self):
         lexer = get_lexer_by_name('text')
         tokens = list(tokenize_string(self.python_code, lexer))
 
         assert tokens == [
             ('',
             u'\n    import this\n\n    var = 6\n    print "this"\n\n    ')
         ]
 
 
 class TestSplitTokenStream(object):
 
     def test_split_token_stream(self):
         lines = list(split_token_stream(
             [('type1', 'some\ntext'), ('type2', 'more\n')]))
 
         assert lines == [
             [('type1', u'some')],
             [('type1', u'text'), ('type2', u'more')],
             [('type2', u'')],
         ]
 
     def test_split_token_stream_other_char(self):
         lines = list(split_token_stream(
             [('type1', 'some\ntext'), ('type2', 'more\n')],
             split_string='m'))
 
         assert lines == [
             [('type1', 'so')],
             [('type1', 'e\ntext'), ('type2', '')],
             [('type2', 'ore\n')],
         ]
 
     def test_split_token_stream_without_char(self):
         lines = list(split_token_stream(
             [('type1', 'some\ntext'), ('type2', 'more\n')],
             split_string='z'))
 
         assert lines == [
             [('type1', 'some\ntext'), ('type2', 'more\n')]
         ]
 
     def test_split_token_stream_single(self):
         lines = list(split_token_stream(
             [('type1', '\n')], split_string='\n'))
 
         assert lines == [
             [('type1', '')],
             [('type1', '')],
         ]
 
     def test_split_token_stream_single_repeat(self):
         lines = list(split_token_stream(
             [('type1', '\n\n\n')], split_string='\n'))
 
         assert lines == [
             [('type1', '')],
             [('type1', '')],
             [('type1', '')],
             [('type1', '')],
         ]
 
     def test_split_token_stream_multiple_repeat(self):
         lines = list(split_token_stream(
             [('type1', '\n\n'), ('type2', '\n\n')], split_string='\n'))
 
         assert lines == [
             [('type1', '')],
             [('type1', '')],
             [('type1', ''), ('type2', '')],
             [('type2', '')],
             [('type2', '')],
         ]
 
 
 class TestRollupTokens(object):
 
     @pytest.mark.parametrize('tokenstream,output', [
         ([],
             []),
         ([('A', 'hell'), ('A', 'o')], [
             ('A', [
                 ('', 'hello')]),
         ]),
         ([('A', 'hell'), ('B', 'o')], [
             ('A', [
                 ('', 'hell')]),
             ('B', [
                 ('', 'o')]),
         ]),
         ([('A', 'hel'), ('A', 'lo'), ('B', ' '), ('A', 'there')], [
             ('A', [
                 ('', 'hello')]),
             ('B', [
                 ('', ' ')]),
             ('A', [
                 ('', 'there')]),
         ]),
     ])
     def test_rollup_tokenstream_without_ops(self, tokenstream, output):
         assert list(rollup_tokenstream(tokenstream)) == output
 
     @pytest.mark.parametrize('tokenstream,output', [
         ([],
             []),
         ([('A', '', 'hell'), ('A', '', 'o')], [
             ('A', [
                 ('', 'hello')]),
         ]),
         ([('A', '', 'hell'), ('B', '', 'o')], [
             ('A', [
                 ('', 'hell')]),
             ('B', [
                 ('', 'o')]),
         ]),
         ([('A', '', 'h'), ('B', '', 'e'), ('C', '', 'y')], [
             ('A', [
                 ('', 'h')]),
             ('B', [
                 ('', 'e')]),
             ('C', [
                 ('', 'y')]),
         ]),
         ([('A', '', 'h'), ('A', '', 'e'), ('C', '', 'y')], [
             ('A', [
                 ('', 'he')]),
             ('C', [
                 ('', 'y')]),
         ]),
         ([('A', 'ins', 'h'), ('A', 'ins', 'e')], [
             ('A', [
                 ('ins', 'he')
             ]),
         ]),
         ([('A', 'ins', 'h'), ('A', 'del', 'e')], [
             ('A', [
                 ('ins', 'h'),
                 ('del', 'e')
             ]),
         ]),
         ([('A', 'ins', 'h'), ('B', 'del', 'e'), ('B', 'del', 'y')], [
             ('A', [
                 ('ins', 'h'),
             ]),
             ('B', [
                 ('del', 'ey'),
             ]),
         ]),
         ([('A', 'ins', 'h'), ('A', 'del', 'e'), ('B', 'del', 'y')], [
             ('A', [
                 ('ins', 'h'),
                 ('del', 'e'),
             ]),
             ('B', [
                 ('del', 'y'),
             ]),
         ]),
         ([('A', '', 'some'), ('A', 'ins', 'new'), ('A', '', 'name')], [
             ('A', [
                 ('', 'some'),
                 ('ins', 'new'),
                 ('', 'name'),
             ]),
         ]),
     ])
     def test_rollup_tokenstream_with_ops(self, tokenstream, output):
         assert list(rollup_tokenstream(tokenstream)) == output
 
 
 class TestRenderTokenStream(object):
 
     @pytest.mark.parametrize('tokenstream,output', [
         (
             [],
             '',
         ),
         (
             [('', '', u'')],
             '<span></span>',
         ),
         (
             [('', '', u'text')],
             '<span>text</span>',
         ),
         (
             [('A', '', u'')],
             '<span class="A"></span>',
         ),
         (
             [('A', '', u'hello')],
             '<span class="A">hello</span>',
         ),
         (
             [('A', '', u'hel'), ('A', '', u'lo')],
             '<span class="A">hello</span>',
         ),
         (
             [('A', '', u'two\n'), ('A', '', u'lines')],
-            '<span class="A">two<nl>\n</nl>lines</span>',
+            '<span class="A">two\nlines</span>',
         ),
         (
             [('A', '', u'\nthree\n'), ('A', '', u'lines')],
-            '<span class="A"><nl>\n</nl>three<nl>\n</nl>lines</span>',
+            '<span class="A">\nthree\nlines</span>',
         ),
         (
             [('', '', u'\n'), ('A', '', u'line')],
-            '<span><nl>\n</nl></span><span class="A">line</span>',
+            '<span>\n</span><span class="A">line</span>',
         ),
         (
             [('', 'ins', u'\n'), ('A', '', u'line')],
-            '<span><ins><nl>\n</nl></ins></span><span class="A">line</span>',
+            '<span><ins>\n</ins></span><span class="A">line</span>',
         ),
         (
             [('A', '', u'hel'), ('A', 'ins', u'lo')],
             '<span class="A">hel<ins>lo</ins></span>',
         ),
         (
             [('A', '', u'hel'), ('A', 'ins', u'l'), ('A', 'ins', u'o')],
             '<span class="A">hel<ins>lo</ins></span>',
         ),
         (
             [('A', '', u'hel'), ('A', 'ins', u'l'), ('A', 'del', u'o')],
             '<span class="A">hel<ins>l</ins><del>o</del></span>',
         ),
         (
             [('A', '', u'hel'), ('B', '', u'lo')],
             '<span class="A">hel</span><span class="B">lo</span>',
         ),
         (
             [('A', '', u'hel'), ('B', 'ins', u'lo')],
             '<span class="A">hel</span><span class="B"><ins>lo</ins></span>',
         ),
     ])
     def test_render_tokenstream_with_ops(self, tokenstream, output):
         html = render_tokenstream(tokenstream)
         assert html == output
 
     @pytest.mark.parametrize('tokenstream,output', [
         (
             [('A', u'hel'), ('A', u'lo')],
             '<span class="A">hello</span>',
         ),
         (
             [('A', u'hel'), ('A', u'l'), ('A', u'o')],
             '<span class="A">hello</span>',
         ),
         (
             [('A', u'hel'), ('A', u'l'), ('A', u'o')],
             '<span class="A">hello</span>',
         ),
         (
             [('A', u'hel'), ('B', u'lo')],
             '<span class="A">hel</span><span class="B">lo</span>',
         ),
         (
             [('A', u'hel'), ('B', u'lo')],
             '<span class="A">hel</span><span class="B">lo</span>',
         ),
     ])
     def test_render_tokenstream_without_ops(self, tokenstream, output):
         html = render_tokenstream(tokenstream)
         assert html == output