Added option to get the stats from numstat instead of diff

The option --numstat of git log gives the statistics of
lines added and removed file.  Hence, it is not necessary
to parser a raw diff.

Another benefit, it is a less verbose log to be processed,
which helps to process long logs.  This also prepares the
code for counting the changes per file type.

Signed-off-by: Germán Póo-Caamaño <gpoo@gnome.org>

diff --git a/README b/README
index 7226541e34b051a538792cb9cfecd151c37e63ea..bc2d6b3f43b8f0302bb51e9ab76873ae4a5ee2dc 100644 (file)
--- a/README
+++ b/README
@@ -20,6 +20,10 @@ Run it like this:
 
    git log -p -M [details] | gitdm [options]
 
+Alternatively, you can run with:
+
+   git log --numstat -M [details] | gitdm -n [options]
+
 The [details] tell git which changesets are of interest; the [options] can
 be:
 
@@ -44,6 +48,8 @@ be:
 
        -l num  Only list the top <num> entries in each report.
 
+    -n  Use --numstat instead of generated patches to get the statistics.
+
        -o file Write text output to the given file (default is stdout).
 
        -r pat  Only generate statistics for changes to files whose 
@@ -68,6 +74,10 @@ looks like:
     git log -p -M v2.6.19..v2.6.20 | \
        gitdm -u -s -a -o results -h results.html
 
+or:
+
+    git log --numstat -M v2.6.19..v2.6.20 | \
+       gitdm -u -s -a -n -o results -h results.html
 
 CONFIGURATION FILE
 

diff --git a/gitdm b/gitdm
index 84b4f5b1cf226e89e23b9d2f2b370c5ac60d4fd8..67eb77b54d7a9cbf9aa096ce0b82d0817185fcad 100755 (executable)
--- a/gitdm
+++ b/gitdm
@@ -37,6 +37,7 @@ DumpDB = 0
 CFName = 'gitdm.config'
 DirName = ''
 Aggregate = 'month'
+Numstat = 0
 
 #
 # Options:
@@ -48,6 +49,7 @@ Aggregate = 'month'
 # -D           Output date statistics
 # -h hfile     HTML output to hfile
 # -l count     Maximum length for output lists
+# -n        Use numstats instead of generated patch from git log
 # -o file      File for text output
 # -r pattern   Restrict to files matching pattern
 # -s           Ignore author SOB lines
@@ -59,9 +61,9 @@ Aggregate = 'month'
 def ParseOpts ():
     global MapUnknown, DevReports
     global DateStats, AuthorSOBs, FileFilter, AkpmOverLt, DumpDB
-    global CFName, CSVFile, DirName, Aggregate
+    global CFName, CSVFile, DirName, Aggregate, Numstat
 
-    opts, rest = getopt.getopt (sys.argv[1:], 'ab:dc:Dh:l:o:r:suwx:z')
+    opts, rest = getopt.getopt (sys.argv[1:], 'ab:dc:Dh:l:no:r:suwx:z')
     for opt in opts:
         if opt[0] == '-a':
             AkpmOverLt = 1
@@ -77,6 +79,8 @@ def ParseOpts ():
             reports.SetHTMLOutput (open (opt[1], 'w'))
         elif opt[0] == '-l':
             reports.SetMaxList (int (opt[1]))
+        elif opt[0] == '-n':
+            Numstat = 1
         elif opt[0] == '-o':
             reports.SetOutput (open (opt[1], 'w'))
         elif opt[0] == '-r':
@@ -248,20 +252,36 @@ def grabpatch():
                 sys.stderr.write ('Funky date: %s\n' % p.date)
                 p.date = Today
             continue
-        #
-        # If we have a file filter, check for file lines.
-        #
-        if FileFilter:
-            ignore = ApplyFileFilter (Line, ignore)
-        #
-        # OK, maybe it's part of the diff itself.
-        #
-        if not ignore:
-            if Padd.match (Line):
-                p.added += 1
-                continue
-            if Prem.match (Line):
-                p.removed += 1
+        if not Numstat:
+            #
+            # If we have a file filter, check for file lines.
+            #
+            if FileFilter:
+                ignore = ApplyFileFilter (Line, ignore)
+            #
+            # OK, maybe it's part of the diff itself.
+            #
+            if not ignore:
+                if Padd.match (Line):
+                    p.added += 1
+                    continue
+                if Prem.match (Line):
+                    p.removed += 1
+        else:
+            # Get the statistics (lines added/removes) using numstats
+            # and without requiring a diff (--numstat instead -p)
+            m = Pnumstat.match (Line)
+            if m:
+                # If we have a file filter, check for file lines.
+                if FileFilter and not FileFilter.search (m.group(3)):
+                    continue
+
+                try:
+                    p.added += int(m.group(1))
+                    p.removed += int(m.group(2))
+                except ValueError:
+                    # A binary file (image, etc.) is marked with '-'
+                    pass
 
     if '@' in p.author.name:
         GripeAboutAuthorName (p.author.name)

diff --git a/patterns.py b/patterns.py
index e63efb60f2a122292f733dc98d3935bda57bd6ac..423c5214486e043809ebf65dc8ef1ddec04e767d 100644 (file)
--- a/patterns.py
+++ b/patterns.py
@@ -37,3 +37,7 @@ PExtMerge = re.compile(r'^ +Merge( branch .* of)? ([^ ]+:[^ ]+)\n$')
 PIntMerge = re.compile(r'^ +(Merge|Pull) .* into .*$')
 # PIntMerge2 = re.compile(r"^ +Merge branch(es)? '.*$")
 PIntMerge2 = re.compile(r"^ +Merge .*$")
+#
+# Another way to get the statistics (per file).  It implies --numstat
+Pnumstat = re.compile('^(\d+|-)\s+(\d+|-)\s+(.*)$')
+Prename = re.compile('(.*)\{(.*) => (.*)\}(.*)')