More todo items and stubs.

TODO.txt

@@ -1,15 +1,6 @@
 - development statistics generator for git
 	- should be as versatile as statcvs / statsvn
 
-- language?
-	- perl or python?
-
-- make git data collection part separate so that portage to other DVCS's is easier
-	- DataCollector
-
-- make output thingies modular as well (HTML first, plain text later etc)
-	- ReportCreator
-
 [Information]
 - git-log
 - git-ls-files
@@ -19,6 +10,7 @@
 - git-rev-list --all
 	- first and last commit
 - git-show-ref --tags
+	- not all tags are tags on refs?
 - git-log |git-shortlog -s
 	- author: number of commits
 - git-what-changed
@@ -33,9 +25,27 @@
 
 - Authors
 	- List of authors
+		- show only first 10 and rest on separate page?
 	- DONE (T): author, commits (%), LOC?, first commit, last commit
 	- (T): Developer of the Month: month, author, commits, LOC?
 
+- Files
+	- Total Files
+	- Average file size
+	- Average revisions per file
+	- (G) File Count: x = date, y = files
+	- (G) Average file size: x = date, y = lines/file
+	- (T) File Extensions (or mime types from "file"?): extension, files (%), lines (%), lines/file
+	- (T) Largest Files?
+	- (T) Files With Most Revisions?
+
+- Activity by Time?
+	- Hour of Day
+	- Day of Week (+ Hour of weekday -> 7x24)
+	- Month of Year
+	- (G?) Last 30 days
+	- (G?) Last 12 months
+
 - (G) Lines of Code: x = date, y = lines
 
 - Tags
@@ -102,3 +112,4 @@
 
 [Misc]
 - use sortable.js ?
+- could show some statistics from last year, month, etc... pisg-like?

statgit

@@ -7,6 +7,11 @@ import os
 import re
 import sys
 
+def getoutput(cmd):
+	print '>> %s' % cmd
+	output = commands.getoutput(cmd)
+	return output
+
 class DataCollector:
 	def __init__(self):
 		pass
@@ -17,7 +22,7 @@ class DataCollector:
 		self.dir = dir
 	
 	##
-	# TODO: get a dictionary of author
+	# : get a dictionary of author
 	def getAuthorInfo(self, author):
 		return None
 	
@@ -32,6 +37,9 @@ class DataCollector:
 	def getLastCommitDate(self):
 		return datetime.datetime.now()
 	
+	def getTags(self):
+		return []
+	
 	def getTotalAuthors(self):
 		return -1
 	
@@ -48,18 +56,18 @@ class GitDataCollector(DataCollector):
 	def collect(self, dir):
 		DataCollector.collect(self, dir)
 
-		self.total_authors = int(commands.getoutput('git-log |git-shortlog -s |wc -l'))
-		self.total_commits = int(commands.getoutput('git-rev-list --all |wc -l'))
-		self.total_files = int(commands.getoutput('git-ls-files |wc -l'))
-		self.total_lines = int(commands.getoutput('git-ls-files |xargs cat |wc -l'))
+		self.total_authors = int(getoutput('git-log |git-shortlog -s |wc -l'))
+		self.total_commits = int(getoutput('git-rev-list --all |wc -l'))
+		self.total_files = int(getoutput('git-ls-files |wc -l'))
+		self.total_lines = int(getoutput('git-ls-files |xargs cat |wc -l'))
 	
 	def getAuthorInfo(self, author):
-		commits = int(commands.getoutput('git-rev-list --all --author="%s" |wc -l' % author))
+		commits = int(getoutput('git-rev-list --all --author="%s" |wc -l' % author))
 		commits_frac = (100 * float(commits)) / self.getTotalCommits()
 		date_first = '0000-00-00'
 		date_last = '0000-00-00'
-		rev_last = commands.getoutput('git-rev-list --all --author="%s" -n 1' % author)
-		rev_first = commands.getoutput('git-rev-list --all --author="%s" |tail -n 1' % author)
+		rev_last = getoutput('git-rev-list --all --author="%s" -n 1' % author)
+		rev_first = getoutput('git-rev-list --all --author="%s" |tail -n 1' % author)
 		date_first = self.revToDate(rev_first)
 		date_last = self.revToDate(rev_last)
 
@@ -67,9 +75,16 @@ class GitDataCollector(DataCollector):
 		return res
 	
 	def getAuthors(self):
-		lines = commands.getoutput('git-rev-list --all --pretty=format:%an |grep -v ^commit |sort |uniq')
+		lines = getoutput('git-rev-list --all --pretty=format:%an |grep -v ^commit |sort |uniq')
+		return lines.split('\n')
+	
+	def getTags(self):
+		lines = getoutput('git-show-ref --tags |cut -d/ -f3')
 		return lines.split('\n')
 	
+	def getTagDate(self, tag):
+		return self.revToDate('tags/' + tag)
+	
 	def getTotalAuthors(self):
 		return self.total_authors
 	
@@ -83,7 +98,7 @@ class GitDataCollector(DataCollector):
 		return self.total_lines
 	
 	def revToDate(self, rev):
-		stamp = int(commands.getoutput('git-log --pretty=format:%%at "%s" -n 1' % rev))
+		stamp = int(getoutput('git-log --pretty=format:%%at "%s" -n 1' % rev))
 		return datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d')
 
 class ReportCreator:
@@ -102,6 +117,7 @@ class HTMLReportCreator(ReportCreator):
 		f.write("""<html>
 <head>
 	<title>StatGit</title>
+	<link rel="stylesheet" href="statgit.css" type="text/css" />
 </head>
 <body>
 """)
@@ -118,6 +134,13 @@ class HTMLReportCreator(ReportCreator):
 		f.write('<dt>Authors</dt><dd>%s</dd>' % data.getTotalAuthors())
 		f.write('</dl>');
 
+		f.write("""<ul>
+<li><a href="activity.html">Activity</a></li>
+<li><a href="authors.html">Authors</a></li>
+<li><a href="files.html">Files</a></li>
+</ul>
+""")
+
 		f.write('<h2>Authors</h2>')
 
 		f.write('<table class="authors">')
@@ -128,10 +151,10 @@ class HTMLReportCreator(ReportCreator):
 		f.write('</table>')
 
 		f.write('<h2>Tags</h2>')
-
 		f.write('<table>')
 		f.write('<tr><th>Name</th><th>Date</th><th>Developers</th></tr>')
-
+		for tag in data.getTags():
+			f.write('<tr><td>%s</td><td></td></tr>' % tag)
 		f.write('</table>')
 
 		f.write('</body>\n</html>');

statgit.css

@@ -0,0 +1,20 @@
+body {
+	color: black;
+	background-color: #cc9;
+}
+
+dt {
+	font-weight: bold;
+	float: left;
+	margin-right: 1em;
+}
+
+dt:after {
+	content: ': ';
+}
+
+dd {
+	display: block;
+	clear: right;
+}
+