[PATCH v2 0/5] git-p4: fix RCS keyword processing encoding errors

[PATCH v2 0/5] git-p4: fix RCS keyword processing encoding errors

[Joel Holdsworth]

This patch-set fixes a family of issues with git-p4's handling of
incoming text data that contains RCS keywords, when those files contain
bytes which are invalid UTF-8 codes.

Among the patches is a fix for the issue, as well as some peripheral
tidy-ups and improvements to the existing code.

This patch-set is compatible and has been tested with both Python 2 and
3, and includes a test.

This v2 version of the patch-set seperates the read/write mode fix (4/5)
out from the RCS byte processing patch (5/5)

Joel Holdsworth (5):
  git-p4: use with statements to close files after use in
    patchRCSKeywords
  git-p4: pre-compile RCS keyword regexes
  git-p4: add raw option to read_pipelines
  git-p4: open temporary patch file for write only
  git-p4: resolve RCS keywords in bytes not utf-8

 git-p4.py             | 66 ++++++++++++++++++-------------------------
 t/t9810-git-p4-rcs.sh | 15 ++++++++++
 2 files changed, 42 insertions(+), 39 deletions(-)

-- 
2.34.1

[PATCH v2 1/5] git-p4: use with statements to close files after use in patchRCSKeywords

[Joel Holdsworth]

Python with statements are used to wrap the execution of a block of code
so that an object can be safely released when execution leaves the
scope.

They are desirable for improving code tidyness, and to ensure that
objects are properly destroyed even when exceptions are thrown.

Signed-off-by: Joel Holdsworth <jholdsworth@nvidia.com>
---
 git-p4.py | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/git-p4.py b/git-p4.py
index 2b4500226a..226cdef424 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -1757,14 +1757,11 @@ 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()
+            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)
             # Forcibly overwrite the original file
             os.unlink(file)
             shutil.move(outFileName, file)
-- 
2.34.1

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

[Joel Holdsworth]

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

[PATCH v2 3/5] git-p4: add raw option to read_pipelines

[Joel Holdsworth]

Previously the read_lines function always decoded the result lines. In
order to improve support for non-decoded binary processing of data in
git-p4.py, this patch adds a raw option to the function that allows
decoding to be disabled.

Signed-off-by: Joel Holdsworth <jholdsworth@nvidia.com>
---
 git-p4.py | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/git-p4.py b/git-p4.py
index 0af83b9c72..509feac2d8 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -340,17 +340,19 @@ def p4_read_pipe(c, ignore_error=False, raw=False):
     real_cmd = p4_build_cmd(c)
     return read_pipe(real_cmd, ignore_error, raw=raw)
 
-def read_pipe_lines(c):
+def read_pipe_lines(c, raw=False):
     if verbose:
         sys.stderr.write('Reading pipe: %s\n' % str(c))
 
     expand = not isinstance(c, list)
     p = subprocess.Popen(c, stdout=subprocess.PIPE, shell=expand)
     pipe = p.stdout
-    val = [decode_text_stream(line) for line in pipe.readlines()]
+    lines = pipe.readlines()
+    if not raw:
+        lines = [decode_text_stream(line) for line in lines]
     if pipe.close() or p.wait():
         die('Command failed: %s' % str(c))
-    return val
+    return lines
 
 def p4_read_pipe_lines(c):
     """Specifically invoke p4 on the command supplied. """
-- 
2.34.1

[PATCH v2 4/5] git-p4: open temporary patch file for write only

[Joel Holdsworth]

The patchRCSKeywords method creates a temporary file in which to store
the patched output data. Previously this file was opened in "w+" mode
(write and read), but the code never reads the contents of the file
while open, so it only needs to be opened in "w" mode (write-only).

Signed-off-by: Joel Holdsworth <jholdsworth@nvidia.com>
---
 git-p4.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/git-p4.py b/git-p4.py
index 509feac2d8..7845210e69 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -1754,7 +1754,7 @@ 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:
+            with os.fdopen(handle, "w") as outFile, open(file, "r") as inFile:
                 for line in inFile.readlines():
                     outFile.write(regexp.sub(r'$\1$', line))
             # Forcibly overwrite the original file
-- 
2.34.1

[PATCH v2 5/5] git-p4: resolve RCS keywords in bytes not utf-8

[Joel Holdsworth]

RCS keywords are strings that are replaced with information from
Perforce. Examples include $Date$, $Author$, $File$, $Change$ etc.

Perforce resolves these by expanding them with their expanded values
when files are synced, but Git's data model requires these expanded
values to be converted back into their unexpanded form.

Previously, git-p4.py would implement this behaviour through the use of
regular expressions. However, the regular expression substitution was
applied using decoded strings i.e. the content of incoming commit diffs
was first decoded from bytes into UTF-8, processed with regular
expressions, then converted back to bytes.

Not only is this behaviour inefficient, but it is also a cause of a
common issue caused by text files containing invalid UTF-8 data. For
files created in Windows, CP1252 Smart Quote Characters (0x93 and 0x94)
are seen fairly frequently. These codes are invalid in UTF-8, so if the
script encountered any file containing them, on Python 2 the symbols
will be corrupted, and on Python 3 the script will fail with an
exception.

This patch replaces this decoding/encoding with bytes object regular
expressions, so that the substitution is performed directly upon the
source data with no conversions.

A test for smart quote handling has been added to the
t9810-git-p4-rcs.sh test suite.

Signed-off-by: Joel Holdsworth <jholdsworth@nvidia.com>
---
 git-p4.py             | 15 ++++++++-------
 t/t9810-git-p4-rcs.sh | 15 +++++++++++++++
 2 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/git-p4.py b/git-p4.py
index 7845210e69..986595bef0 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -56,8 +56,8 @@
 
 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]+)?\$')
+re_ko_keywords = re.compile(br'\$(Id|Header)(:[^$\n]+)?\$')
+re_k_keywords = re.compile(br'\$(Id|Header|Author|Date|DateTime|Change|File|Revision)(:[^$\n]+)?\$')
 
 def p4_build_cmd(cmd):
     """Build a suitable p4 command line.
@@ -1754,9 +1754,9 @@ 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:
+            with os.fdopen(handle, "wb") as outFile, open(file, "rb") as inFile:
                 for line in inFile.readlines():
-                    outFile.write(regexp.sub(r'$\1$', line))
+                    outFile.write(regexp.sub(br'$\1$', line))
             # Forcibly overwrite the original file
             os.unlink(file)
             shutil.move(outFileName, file)
@@ -2089,7 +2089,9 @@ def applyCommit(self, id):
                     regexp = p4_keywords_regexp_for_file(file)
                     if regexp:
                         # this file is a possibility...look for RCS keywords.
-                        for line in read_pipe_lines(["git", "diff", "%s^..%s" % (id, id), file]):
+                        for line in read_pipe_lines(
+                            ["git", "diff", "%s^..%s" % (id, id), file],
+                            raw=True):
                             if regexp.search(line):
                                 if verbose:
                                     print("got keyword match on %s in %s in %s" % (regex.pattern, line, file))
@@ -3020,8 +3022,7 @@ def streamOneP4File(self, file, contents):
         # even though in theory somebody may want that.
         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)))]
+            contents = [regexp.sub(br'$\1$', c) for c in contents]
 
         if self.largeFileSystem:
             (git_mode, contents) = self.largeFileSystem.processContent(git_mode, relPath, contents)
diff --git a/t/t9810-git-p4-rcs.sh b/t/t9810-git-p4-rcs.sh
index e3836888ec..5fe83315ec 100755
--- a/t/t9810-git-p4-rcs.sh
+++ b/t/t9810-git-p4-rcs.sh
@@ -4,6 +4,8 @@ test_description='git p4 rcs keywords'
 
 . ./lib-git-p4.sh
 
+CP1252="\223\224"
+
 test_expect_success 'start p4d' '
 	start_p4d
 '
@@ -32,6 +34,9 @@ test_expect_success 'init depot' '
 		p4 submit -d "filek" &&
 		p4 add -t text+ko fileko &&
 		p4 submit -d "fileko" &&
+		printf "$CP1252" >fileko_cp1252 &&
+		p4 add -t text+ko fileko_cp1252 &&
+		p4 submit -d "fileko_cp1252" &&
 		p4 add -t text file_text &&
 		p4 submit -d "file_text"
 	)
@@ -359,4 +364,14 @@ test_expect_failure 'Add keywords in git which do not match the default p4 value
 	)
 '
 
+test_expect_success 'check cp1252 smart quote are preserved through RCS keyword processing' '
+	test_when_finished cleanup_git &&
+	git p4 clone --dest="$git" //depot &&
+	(
+		cd "$git" &&
+		printf "$CP1252" >expect &&
+		test_cmp_bin expect fileko_cp1252
+	)
+'
+
 test_done
-- 
2.34.1