# HG changeset patch
# User Bryan O'Sullivan <bos@serpentine.com>
# Date 2005-09-21 18:44:08
# Node ID a6ffcebd331532a3ebafa77b42c3949561cc64c1
# Parent  141951276ba1d5729a67215ae9f28fc641f87607

Enhance the file filtering capabilities.

We now allow filtering through either pipes or pairs of temporary
files.  The latter appear to be mandatory for use on Windows.


diff --git a/doc/hgrc.5.txt b/doc/hgrc.5.txt
--- a/doc/hgrc.5.txt
+++ b/doc/hgrc.5.txt
@@ -67,20 +67,53 @@ decode/encode::
   localization/canonicalization of files.
 
   Filters consist of a filter pattern followed by a filter command.
-  The command must accept data on stdin and return the transformed
-  data on stdout.
+  Filter patterns are globs by default, rooted at the repository
+  root.  For example, to match any file ending in ".txt" in the root
+  directory only, use the pattern "*.txt".  To match any file ending
+  in ".c" anywhere in the repository, use the pattern "**.c".
 
-  Example:
+  The filter command can start with a specifier, either "pipe:" or
+  "tempfile:".  If no specifier is given, "pipe:" is used by default.
+
+  A "pipe:" command must accept data on stdin and return the
+  transformed data on stdout.
+
+  Pipe example:
 
     [encode]
     # uncompress gzip files on checkin to improve delta compression
     # note: not necessarily a good idea, just an example
-    *.gz = gunzip
+    *.gz = pipe: gunzip
 
     [decode]
-    # recompress gzip files when writing them to the working dir
+    # recompress gzip files when writing them to the working dir (we
+    # can safely omit "pipe:", because it's the default)
     *.gz = gzip
 
+  A "tempfile:" command is a template.  The string INFILE is replaced
+  with the name of a temporary file that contains the data to be
+  filtered by the command.  The string OUTFILE is replaced with the
+  name of an empty temporary file, where the filtered data must be
+  written by the command.
+
+  NOTE: the tempfile mechanism is recommended for Windows systems,
+  where the standard shell I/O redirection operators often have
+  strange effects.  In particular, if you are doing line ending
+  conversion on Windows using the popular dos2unix and unix2dos
+  programs, you *must* use the tempfile mechanism, as using pipes will
+  corrupt the contents of your files.
+
+  Tempfile example:
+
+    [encode]
+    # convert files to unix line ending conventions on checkin
+    **.txt = tempfile: dos2unix -n INFILE OUTFILE
+
+    [decode]
+    # convert files to windows line ending conventions when writing
+    # them to the working dir
+    **.txt = tempfile: unix2dos -n INFILE OUTFILE
+
 hooks::
   Commands that get automatically executed by various actions such as
   starting or finishing a commit.
diff --git a/mercurial/util.py b/mercurial/util.py
--- a/mercurial/util.py
+++ b/mercurial/util.py
@@ -12,10 +12,10 @@ platform-specific details from the core.
 
 import os, errno
 from demandload import *
-demandload(globals(), "re cStringIO shutil popen2 threading")
+demandload(globals(), "re cStringIO shutil popen2 tempfile threading")
 
-def filter(s, cmd):
-    "filter a string through a command that transforms its input to its output"
+def pipefilter(s, cmd):
+    '''filter string S through command CMD, returning its output'''
     (pout, pin) = popen2.popen2(cmd, -1, 'b')
     def writer():
         pin.write(s)
@@ -30,6 +30,45 @@ def filter(s, cmd):
     w.join()
     return f
 
+def tempfilter(s, cmd):
+    '''filter string S through a pair of temporary files with CMD.
+    CMD is used as a template to create the real command to be run,
+    with the strings INFILE and OUTFILE replaced by the real names of
+    the temporary files generated.'''
+    inname, outname = None, None
+    try:
+        infd, inname = tempfile.mkstemp(prefix='hgfin')
+        fp = os.fdopen(infd, 'wb')
+        fp.write(s)
+        fp.close()
+        outfd, outname = tempfile.mkstemp(prefix='hgfout')
+        os.close(outfd)
+        cmd = cmd.replace('INFILE', inname)
+        cmd = cmd.replace('OUTFILE', outname)
+        code = os.system(cmd)
+        if code: raise Abort("command '%s' failed: %s" %
+                             (cmd, explain_exit(code)))
+        return open(outname, 'rb').read()
+    finally:
+        try:
+            if inname: os.unlink(inname)
+        except: pass
+        try:
+            if outname: os.unlink(outname)
+        except: pass
+
+filtertable = {
+    'tempfile:': tempfilter,
+    'pipe:': pipefilter,
+    }
+
+def filter(s, cmd):
+    "filter a string through a command that transforms its input to its output"
+    for name, fn in filtertable.iteritems():
+        if cmd.startswith(name):
+            return fn(s, cmd[len(name):].lstrip())
+    return pipefilter(s, cmd)
+
 def patch(strip, patchname, ui):
     """apply the patch <patchname> to the working directory.
     a list of patched files is returned"""
@@ -43,7 +82,7 @@ def patch(strip, patchname, ui):
             files.setdefault(pf, 1)
     code = fp.close()
     if code:
-        raise Abort("patch command failed: exit status %s " % code)
+        raise Abort("patch command failed: %s" % explain_exit(code))
     return files.keys()
 
 def binary(s):