From 780c0fd57ec83d40ea511f2fce171c1ea378ae34 Mon Sep 17 00:00:00 2001
From: Sylvain Joyeux <sylvain.joyeux@m4x.org>
Date: Thu, 29 May 2014 22:01:23 +0200
Subject: [PATCH] implement a way to limit the statistics to commits after a
 start date

This is really useful when computing statistics over a set of
repositories, where some repositories are much older than other.

Signed-off-by: Heikki Hokkanen <hoxu@users.sf.net>
---
 gitstats | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/gitstats b/gitstats
index 9e639df..0b444b7 100755
--- a/gitstats
+++ b/gitstats
@@ -48,6 +48,7 @@ conf = {
 	'project_name': '',
 	'merge_authors': {},
 	'processes': 8,
+	'start_date': ''
 }
 
 def getpipeoutput(cmds, quiet = False):
@@ -72,6 +73,12 @@ def getpipeoutput(cmds, quiet = False):
 	exectime_external += (end - start)
 	return output.rstrip('\n')
 
+def getlogrange(defaultrange = 'HEAD', end_only = True):
+	commit_range = getcommitrange(defaultrange, end_only)
+	if len(conf['start_date']) > 0:
+		return '--since=%s %s' % (conf['start_date'], commit_range)
+	return commit_range
+
 def getcommitrange(defaultrange = 'HEAD', end_only = False):
 	if len(conf['commit_end']) > 0:
 		if end_only or len(conf['commit_begin']) == 0:
@@ -280,7 +287,7 @@ class GitDataCollector(DataCollector):
 	def collect(self, dir):
 		DataCollector.collect(self, dir)
 
-		self.total_authors += int(getpipeoutput(['git shortlog -s %s' % getcommitrange(), 'wc -l']))
+		self.total_authors += int(getpipeoutput(['git shortlog -s %s' % getlogrange(), 'wc -l']))
 		#self.total_lines = int(getoutput('git-ls-files -z |xargs -0 cat |wc -l'))
 
 		# tags
@@ -323,7 +330,7 @@ class GitDataCollector(DataCollector):
 
 		# Collect revision statistics
 		# Outputs "<stamp> <date> <time> <timezone> <author> '<' <mail> '>'"
-		lines = getpipeoutput(['git rev-list --pretty=format:"%%at %%ai %%aN <%%aE>" %s' % getcommitrange('HEAD'), 'grep -v ^commit']).split('\n')
+		lines = getpipeoutput(['git rev-list --pretty=format:"%%at %%ai %%aN <%%aE>" %s' % getlogrange('HEAD'), 'grep -v ^commit']).split('\n')
 		for line in lines:
 			parts = line.split(' ', 4)
 			author = ''
@@ -432,7 +439,7 @@ class GitDataCollector(DataCollector):
 			self.commits_by_timezone[timezone] = self.commits_by_timezone.get(timezone, 0) + 1
 
 		# outputs "<stamp> <files>" for each revision
-		revlines = getpipeoutput(['git rev-list --pretty=format:"%%at %%T" %s' % getcommitrange('HEAD'), 'grep -v ^commit']).strip().split('\n')
+		revlines = getpipeoutput(['git rev-list --pretty=format:"%%at %%T" %s' % getlogrange('HEAD'), 'grep -v ^commit']).strip().split('\n')
 		lines = []
 		revs_to_read = []
 		time_rev_count = []
@@ -534,7 +541,7 @@ class GitDataCollector(DataCollector):
 		extra = ''
 		if conf['linear_linestats']:
 			extra = '--first-parent -m'
-		lines = getpipeoutput(['git log --shortstat %s --pretty=format:"%%at %%aN" %s' % (extra, getcommitrange('HEAD'))]).split('\n')
+		lines = getpipeoutput(['git log --shortstat %s --pretty=format:"%%at %%aN" %s' % (extra, getlogrange('HEAD'))]).split('\n')
 		lines.reverse()
 		files = 0; inserted = 0; deleted = 0; total_lines = 0
 		author = None
@@ -590,7 +597,7 @@ class GitDataCollector(DataCollector):
 		# Similar to the above, but never use --first-parent
 		# (we need to walk through every commit to know who
 		# committed what, not just through mainline)
-		lines = getpipeoutput(['git log --shortstat --date-order --pretty=format:"%%at %%aN" %s' % (getcommitrange('HEAD'))]).split('\n')
+		lines = getpipeoutput(['git log --shortstat --date-order --pretty=format:"%%at %%aN" %s' % (getlogrange('HEAD'))]).split('\n')
 		lines.reverse()
 		files = 0; inserted = 0; deleted = 0
 		author = None