[PATCH v2 2/5] git-p4: pre-compile RCS keyword regexes

[Joel Holdsworth <jholdsworth@nvidia.com>]

Previously git-p4.py would compile one of two regular expressions for
ever RCS keyword-enabled file. This patch improves simplifies the code
by pre-compiling the two regular expressions when the script first
loads.

Signed-off-by: Joel Holdsworth <jholdsworth@nvidia.com>
---
 git-p4.py | 48 ++++++++++++++++++------------------------------
 1 file changed, 18 insertions(+), 30 deletions(-)

diff --git a/git-p4.py b/git-p4.py
index 226cdef424..0af83b9c72 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -56,6 +56,9 @@
 
 p4_access_checked = False
 
+re_ko_keywords = re.compile(r'\$(Id|Header)(:[^$\n]+)?\$')
+re_k_keywords = re.compile(r'\$(Id|Header|Author|Date|DateTime|Change|File|Revision)(:[^$\n]+)?\$')
+
 def p4_build_cmd(cmd):
     """Build a suitable p4 command line.
 
@@ -577,20 +580,12 @@ def p4_type(f):
 #
 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'
+            return re_ko_keywords
         elif "k" in type_mods:
-            kwords = 'Id|Header|Author|Date|DateTime|Change|File|Revision'
+            return re_k_keywords
         else:
             return None
-        pattern = r"""
-            \$              # Starts with a dollar, followed by...
-            (%s)            # one of the keywords, followed by...
-            (:[^$\n]+)?     # possibly an old expansion, followed by...
-            \$              # another dollar
-            """ % kwords
-        return pattern
     else:
         return None
 
@@ -1753,15 +1748,13 @@ def prepareLogMessage(self, template, message, jobs):
 
         return result
 
-    def patchRCSKeywords(self, file, pattern):
-        # Attempt to zap the RCS keywords in a p4 controlled file matching the given pattern
+    def patchRCSKeywords(self, file, regexp):
+        # Attempt to zap the RCS keywords in a p4 controlled file matching the given regex
         (handle, outFileName) = tempfile.mkstemp(dir='.')
         try:
             with os.fdopen(handle, "w+") as outFile, open(file, "r") as inFile:
-                regexp = re.compile(pattern, re.VERBOSE)
                 for line in inFile.readlines():
-                    line = regexp.sub(r'$\1$', line)
-                    outFile.write(line)
+                    outFile.write(regexp.sub(r'$\1$', line))
             # Forcibly overwrite the original file
             os.unlink(file)
             shutil.move(outFileName, file)
@@ -2088,25 +2081,22 @@ def applyCommit(self, id):
             # the patch to see if that's possible.
             if gitConfigBool("git-p4.attemptRCSCleanup"):
                 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:
+                    regexp = p4_keywords_regexp_for_file(file)
+                    if regexp:
                         # 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
+                                    print("got keyword match on %s in %s in %s" % (regex.pattern, line, file))
+                                kwfiles[file] = regexp
                                 break
 
-                for file in kwfiles:
+                for file, regexp in kwfiles.items():
                     if verbose:
-                        print("zapping %s with %s" % (line,pattern))
+                        print("zapping %s with %s" % (line, regexp.pattern))
                     # File is being deleted, so not open in p4.  Must
                     # disable the read-only bit on windows.
                     if self.isWindows and file not in editedFiles:
@@ -3026,12 +3016,10 @@ def streamOneP4File(self, file, contents):
 
         # Note that we do not try to de-mangle keywords on utf16 files,
         # even though in theory somebody may want that.
-        pattern = p4_keywords_regexp_for_type(type_base, type_mods)
-        if pattern:
-            regexp = re.compile(pattern, re.VERBOSE)
-            text = ''.join(decode_text_stream(c) for c in contents)
-            text = regexp.sub(r'$\1$', text)
-            contents = [ encode_text_stream(text) ]
+        regexp = p4_keywords_regexp_for_type(type_base, type_mods)
+        if regexp:
+            contents = [encode_text_stream(regexp.sub(
+                r'$\1$', ''.join(decode_text_stream(c) for c in contents)))]
 
         if self.largeFileSystem:
             (git_mode, contents) = self.largeFileSystem.processContent(git_mode, relPath, contents)
-- 
2.34.1