filelog: test behaviour for data starting with "\1\n"

Because "\1\n" is a separator for metadata, data starting with "\1\n" is
handled specifically. It was not tested.

size() call return incorrect data if original data had been "\1\n-escaped".
There's no obvious way to fix it for now, just flag the error in the code
and add an "expected failure" kind of test.

tests/test-filelog

@@ -0,0 +1,50 b''
+#!/usr/bin/env python
+"""
+Tests the behaviour of filelog w.r.t. data starting with '\1\n'
+"""
+from mercurial import ui, hg
+from mercurial.node import nullid, hex
+
+myui = ui.ui()
+repo = hg.repository(myui, path='.', create=True)
+
+fl = repo.file('foobar')
+
+def addrev(text, renamed=False):
+    if renamed:
+        # data doesnt matter. Just make sure filelog.renamed() returns True
+        meta = dict(copyrev=hex(nullid), copy='bar')
+    else:
+        meta = {}
+
+    t = repo.transaction('commit')
+    try:
+        node = fl.add(text, meta, t, 0, nullid, nullid)
+        return node
+    finally:
+        t.close()
+
+def error(text):
+    print 'ERROR: ' + text
+
+textwith = '\1\nfoo'
+without = 'foo'
+
+node = addrev(textwith)
+if not textwith == fl.read(node):
+    error('filelog.read for data starting with \\1\\n')
+if fl.cmp(node, textwith) or not fl.cmp(node, without):
+    error('filelog.cmp for data starting with \\1\\n')
+if fl.size(0) != len(textwith):
+    error('FIXME: This is a known failure of filelog.size for data starting '
+        'with \\1\\n')
+
+node = addrev(textwith, renamed=True)
+if not textwith == fl.read(node):
+    error('filelog.read for a renaming + data starting with \\1\\n')
+if fl.cmp(node, textwith) or not fl.cmp(node, without):
+    error('filelog.cmp for a renaming + data starting with \\1\\n')
+if fl.size(1) != len(textwith):
+    error('filelog.size for a renaming + data starting with \\1\\n')
+
+print 'OK.'

tests/test-filelog.out

@@ -0,0 +1,2 b''
+ERROR: FIXME: This is a known failure of filelog.size for data starting with \1\n
+OK.

mercurial/filelog.py

@@ -1,69 +1,70 b''
 # filelog.py - file history class for mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import revlog
 
 class filelog(revlog.revlog):
     def __init__(self, opener, path):
         revlog.revlog.__init__(self, opener,
                         "/".join(("data", path + ".i")))
 
     def read(self, node):
         t = self.revision(node)
         if not t.startswith('\1\n'):
             return t
         s = t.index('\1\n', 2)
         return t[s + 2:]
 
     def _readmeta(self, node):
         t = self.revision(node)
         if not t.startswith('\1\n'):
             return {}
         s = t.index('\1\n', 2)
         mt = t[2:s]
         m = {}
         for l in mt.splitlines():
             k, v = l.split(": ", 1)
             m[k] = v
         return m
 
     def add(self, text, meta, transaction, link, p1=None, p2=None):
         if meta or text.startswith('\1\n'):
             mt = ["%s: %s\n" % (k, v) for k, v in sorted(meta.iteritems())]
             text = "\1\n%s\1\n%s" % ("".join(mt), text)
         return self.addrevision(text, transaction, link, p1, p2)
 
     def renamed(self, node):
         if self.parents(node)[0] != revlog.nullid:
             return False
         m = self._readmeta(node)
         if m and "copy" in m:
             return (m["copy"], revlog.bin(m["copyrev"]))
         return False
 
     def size(self, rev):
         """return the size of a given revision"""
 
         # for revisions with renames, we have to go the slow way
         node = self.node(rev)
         if self.renamed(node):
             return len(self.read(node))
 
+        # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
         return revlog.revlog.size(self, rev)
 
     def cmp(self, node, text):
         """compare text with a given file revision
 
         returns True if text is different than what is stored.
         """
 
         # for renames, we have to go the slow way
         if text.startswith('\1\n') or self.renamed(node):
             t2 = self.read(node)
             return t2 != text
 
         return revlog.revlog.cmp(self, node, text)