gitdm patch ...

Hi guys,

	I knocked up a patch to generate some per-month, by-affiliation
statistics from the gitdm output; attached for interest or merging.

	A sample of the output, complete with OO.o data-pilot, and pretty chart
is here:

http://www.gnome.org/~michael/data/2008-09-29-linux-stats.ods

	with chart here:
	http://www.gnome.org/~michael/images/2008-09-29-kernel-active.png

	caption being:

	"Graph showing number and affiliation of active kernel developers
(contributing more than 100 lines per month). Quick affiliation key,
from bottom up: Unknown, No-Affiliation, IBM, RedHat, Novell, Intel ..."

	These are as yet not published, I plan to use them as a comparison to
OO.o's somewhat mediocre equivalents; hope to go live with them soon
(and fix the horrible bugs in stacked area charts to make them actually
pretty ).

	HTH,

		Michael.

--
 michael.meeks@novell.com  <><, Pseudo Engineer, itinerant idiot

Signed-off-by: Jonathan Corbet <corbet@lwn.net>

diff --git a/csv.py b/csv.py
new file mode 100644 (file)
index 0000000..34ea10a
--- /dev/null
+++ b/csv.py
@@ -0,0 +1,38 @@
+#
+# aggregate per-month statistics for people
+#
+import sys, datetime
+
+class CSVStat:
+    def __init__ (self, name, employer, date):
+        self.name = name
+        self.employer = employer
+        self.added = self.removed = 0
+        self.date = date
+    def accumulate (self, p):
+        self.added = self.added + p.added
+        self.removed = self.removed + p.removed
+
+PeriodCommitHash = { }
+
+def AccumulatePatch (p):
+    date = "%.2d-%.2d-01"%(p.date.year, p.date.month)
+    authdatekey = "%s-%s"%(p.author.name, date)
+    if authdatekey not in PeriodCommitHash:
+        empl = p.author.emailemployer (p.email, p.date)
+        stat = CSVStat (p.author.name, empl, date)
+        PeriodCommitHash[authdatekey] = stat
+    else:
+        stat = PeriodCommitHash[authdatekey]
+    stat.accumulate (p)
+
+def OutputCSV (file):
+    if file is None:
+        return
+    file.write ("Name\tAffliation\tDate\tAdded\tRemoved\n")
+    for date, stat in PeriodCommitHash.items():
+        # sanitise names " is common and \" sometimes too
+        empl_name = stat.employer.name.replace ("\"", ".").replace ("\\", ".")
+        author_name = stat.name.replace ("\"", ".").replace ("\\", ".")
+        file.write ("\"%s\"\t\"%s\"\t%s\t%d\t%d\n"%(author_name, empl_name, stat.date, \
+                                                    stat.added, stat.removed))

diff --git a/gitdm b/gitdm
index 20ec2573e742f1275fdf2b272bb573b401e7d3d9..1c3adc771f11042132f7e47c67a17ac86aa07d99 100755 (executable)
--- a/gitdm
+++ b/gitdm
@@ -11,7 +11,7 @@
 # Public License, version 2.
 
 
-import database, ConfigFile
+import database, csv, ConfigFile
 import getopt, datetime
 import os, re, sys, rfc822, string
 from patterns import *
@@ -30,6 +30,7 @@ DevReports = 1
 DateStats = 0
 AuthorSOBs = 1
 FileFilter = None
+CSVFile = None
 AkpmOverLt = 0
 DumpDB = 0
 CFName = 'gitdm.config'
@@ -46,14 +47,15 @@ CFName = 'gitdm.config'
 # -r pattern   Restrict to files matching pattern
 # -s           Ignore author SOB lines
 # -u           Map unknown employers to '(Unknown)'
+# -x file.csv   Export raw statistics as CSV
 # -z           Dump out the hacker database at completion
 
 def ParseOpts ():
     global Outfile, ListCount, MapUnknown, HTMLfile, DevReports
     global DateStats, AuthorSOBs, FileFilter, AkpmOverLt, DumpDB
-    global CFName
+    global CFName, CSVFile
 
-    opts, rest = getopt.getopt (sys.argv[1:], 'adc:Dh:l:o:r:suz')
+    opts, rest = getopt.getopt (sys.argv[1:], 'adc:Dh:l:o:r:sux:z')
     for opt in opts:
         if opt[0] == '-a':
             AkpmOverLt = 1
@@ -76,6 +78,9 @@ def ParseOpts ():
             AuthorSOBs = 0
         elif opt[0] == '-u':
             MapUnknown = 1
+        elif opt[0] == '-x':
+            CSVFile = open (opt[1], 'w')
+            print "open output file " + opt[1] + "\n"
         elif opt[0] == '-z':
             DumpDB = 1
         
@@ -260,7 +265,6 @@ THead = '''<p>
 <tr><th colspan=3>%s</th></tr>
 '''
 
-
 def BeginReport (title):
     global HTMLclass
     
@@ -459,6 +463,7 @@ while (1):
         for sobemail, sob in p.sobs:
             sob.addsob (p)
     CSCount += 1
+    csv.AccumulatePatch (p)
 print >> sys.stderr, 'Grabbing changesets...done'
 
 if DumpDB:
@@ -479,6 +484,10 @@ if DateStats:
     PrintDateStats ()
     sys.exit(0)
 
+csv.OutputCSV (CSVFile)
+if CSVFile is not None:
+        CSVFile.close ()
+
 if DevReports:
     ReportByPCount (hlist)
     ReportByLChanged (hlist)