git-p4: add initial support for RCS keywords

RCS keywords cause problems for git-p4 as perforce always
expands them (if +k is set) and so when applying the patch,
git reports that the files have been modified by both sides,
when in fact they haven't.

This change means that when git-p4 detects a problem applying
a patch, it will check to see if keyword expansion could be
the culprit. If it is, it strips the keywords in the p4
repository so that they match what git is expecting. It then
has another go at applying the patch.

This behaviour is enabled with a new git-p4 configuration
option and is off by default.

Acked-by: Pete Wyckoff <pw@padd.com>
Signed-off-by: Luke Diamand <luke@diamand.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 108 insertions, 10 deletions

diff --git a/contrib/fast-import/git-p4 b/contrib/fast-import/git-p4
index a78d9c549..c8b6c8abe 100755
--- a/contrib/fast-import/git-p4
+++ b/contrib/fast-import/git-p4
@@ -10,7 +10,7 @@
 
 import optparse, sys, os, marshal, subprocess, shelve
 import tempfile, getopt, os.path, time, platform
-import re
+import re, shutil
 
 verbose = False
 
@@ -186,6 +186,47 @@ def split_p4_type(p4type):
         mods = s[1]
     return (base, mods)
 
+#
+# return the raw p4 type of a file (text, text+ko, etc)
+#
+def p4_type(file):
+    results = p4CmdList(["fstat", "-T", "headType", file])
+    return results[0]['headType']
+
+#
+# Given a type base and modifier, return a regexp matching
+# the keywords that can be expanded in the file
+#
+def p4_keywords_regexp_for_type(base, type_mods):
+    if base in ("text", "unicode", "binary"):
+        kwords = None
+        if "ko" in type_mods:
+            kwords = 'Id|Header'
+        elif "k" in type_mods:
+            kwords = 'Id|Header|Author|Date|DateTime|Change|File|Revision'
+        else:
+            return None
+        pattern = r"""
+            \$              # Starts with a dollar, followed by...
+            (%s)            # one of the keywords, followed by...
+            (:[^$]+)?       # possibly an old expansion, followed by...
+            \$              # another dollar
+            """ % kwords
+        return pattern
+    else:
+        return None
+
+#
+# Given a file, return a regexp matching the possible
+# RCS keywords that will be expanded, or None for files
+# with kw expansion turned off.
+#
+def p4_keywords_regexp_for_file(file):
+    if not os.path.exists(file):
+        return None
+    else:
+        (type_base, type_mods) = split_p4_type(p4_type(file))
+        return p4_keywords_regexp_for_type(type_base, type_mods)
 
 def setP4ExecBit(file, mode):
     # Reopens an already open file and changes the execute bit to match
@@ -753,6 +794,29 @@ class P4Submit(Command, P4UserMap):
 
         return result
 
+    def patchRCSKeywords(self, file, pattern):
+        # Attempt to zap the RCS keywords in a p4 controlled file matching the given pattern
+        (handle, outFileName) = tempfile.mkstemp(dir='.')
+        try:
+            outFile = os.fdopen(handle, "w+")
+            inFile = open(file, "r")
+            regexp = re.compile(pattern, re.VERBOSE)
+            for line in inFile.readlines():
+                line = regexp.sub(r'$\1$', line)
+                outFile.write(line)
+            inFile.close()
+            outFile.close()
+            # Forcibly overwrite the original file
+            os.unlink(file)
+            shutil.move(outFileName, file)
+        except:
+            # cleanup our temporary file
+            os.unlink(outFileName)
+            print "Failed to strip RCS keywords in %s" % file
+            raise
+
+        print "Patched up RCS keywords in %s" % file
+
     def p4UserForCommit(self,id):
         # Return the tuple (perforce user,git email) for a given git commit id
         self.getUserMapFromPerforceServer()
@@ -918,6 +982,7 @@ class P4Submit(Command, P4UserMap):
         filesToDelete = set()
         editedFiles = set()
         filesToChangeExecBit = {}
+
         for line in diff:
             diff = parseDiffTreeEntry(line)
             modifier = diff['status']
@@ -964,9 +1029,45 @@ class P4Submit(Command, P4UserMap):
         patchcmd = diffcmd + " | git apply "
         tryPatchCmd = patchcmd + "--check -"
         applyPatchCmd = patchcmd + "--check --apply -"
+        patch_succeeded = True
 
         if os.system(tryPatchCmd) != 0:
+            fixed_rcs_keywords = False
+            patch_succeeded = False
             print "Unfortunately applying the change failed!"
+
+            # Patch failed, maybe it's just RCS keyword woes. Look through
+            # the patch to see if that's possible.
+            if gitConfig("git-p4.attemptRCSCleanup","--bool") == "true":
+                file = None
+                pattern = None
+                kwfiles = {}
+                for file in editedFiles | filesToDelete:
+                    # did this file's delta contain RCS keywords?
+                    pattern = p4_keywords_regexp_for_file(file)
+
+                    if pattern:
+                        # this file is a possibility...look for RCS keywords.
+                        regexp = re.compile(pattern, re.VERBOSE)
+                        for line in read_pipe_lines(["git", "diff", "%s^..%s" % (id, id), file]):
+                            if regexp.search(line):
+                                if verbose:
+                                    print "got keyword match on %s in %s in %s" % (pattern, line, file)
+                                kwfiles[file] = pattern
+                                break
+
+                for file in kwfiles:
+                    if verbose:
+                        print "zapping %s with %s" % (line,pattern)
+                    self.patchRCSKeywords(file, kwfiles[file])
+                    fixed_rcs_keywords = True
+
+            if fixed_rcs_keywords:
+                print "Retrying the patch with RCS keywords cleaned up"
+                if os.system(tryPatchCmd) == 0:
+                    patch_succeeded = True
+
+        if not patch_succeeded:
             print "What do you want to do?"
             response = "x"
             while response != "s" and response != "a" and response != "w":
@@ -1585,15 +1686,12 @@ class P4Sync(Command, P4UserMap):
 
         # Note that we do not try to de-mangle keywords on utf16 files,
         # even though in theory somebody may want that.
-        if type_base in ("text", "unicode", "binary"):
-            if "ko" in type_mods:
-                text = ''.join(contents)
-                text = re.sub(r'\$(Id|Header):[^$]*\$', r'$\1$', text)
-                contents = [ text ]
-            elif "k" in type_mods:
-                text = ''.join(contents)
-                text = re.sub(r'\$(Id|Header|Author|Date|DateTime|Change|File|Revision):[^$]*\$', r'$\1$', text)
-                contents = [ text ]
+        pattern = p4_keywords_regexp_for_type(type_base, type_mods)
+        if pattern:
+            regexp = re.compile(pattern, re.VERBOSE)
+            text = ''.join(contents)
+            text = regexp.sub(r'$\1$', text)
+            contents = [ text ]
 
         self.gitStream.write("M %s inline %s\n" % (git_mode, relPath))