Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support --no-merges #57

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Support --no-merges #57

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
27c24a3
Add a .gitignore
jaywink Jan 24, 2016
e9d16e0
Implement support for filtering out merge commits
jaywink Jan 24, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
123 changes: 123 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,123 @@
### Python template
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class

# C extensions
*.so

# Distribution / packaging
.Python
env/
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
*.egg-info/
.installed.cfg
*.egg

# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec

# Installer logs
pip-log.txt
pip-delete-this-directory.txt

# Unit test / coverage reports
htmlcov/
.tox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*,cover

# Translations
*.mo
*.pot

# Django stuff:
*.log

# Sphinx documentation
docs/_build/

# PyBuilder
target/
### JetBrains template
# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio

*.iml

## Directory-based project format:
.idea/
# if you remove the above rule, at least ignore the following:

# User-specific stuff:
# .idea/workspace.xml
# .idea/tasks.xml
# .idea/dictionaries

# Sensitive or high-churn files:
# .idea/dataSources.ids
# .idea/dataSources.xml
# .idea/sqlDataSources.xml
# .idea/dynamic.xml
# .idea/uiDesigner.xml

# Gradle:
# .idea/gradle.xml
# .idea/libraries

# Mongo Explorer plugin:
# .idea/mongoSettings.xml

## File-based project format:
*.ipr
*.iws

## Plugin-specific files:

# IntelliJ
/out/

# mpeltonen/sbt-idea plugin
.idea_modules/

# JIRA plugin
atlassian-ide-plugin.xml

# Crashlytics plugin (for Android Studio and IntelliJ)
com_crashlytics_export_strings.xml
crashlytics.properties
crashlytics-build.properties
### SublimeText template
# cache files for sublime text
*.tmlanguage.cache
*.tmPreferences.cache
*.stTheme.cache

# workspace files are user-specific
*.sublime-workspace

# project files should be checked into the repository, unless a significant
# proportion of contributors will probably not be using SublimeText
# *.sublime-project

# sftp configuration file
sftp-config.json

# Created by .ignore support plugin (hsz.mobi)
79 changes: 42 additions & 37 deletions gitstats
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,8 @@ conf = {
'linear_linestats': 1,
'project_name': '',
'processes': 8,
'start_date': ''
'start_date': '',
'no_merges': 0,
}

def getpipeoutput(cmds, quiet = False):
Expand Down Expand Up @@ -133,7 +134,7 @@ def getnumoflinesinblob(ext_blob):
ext, blob_id = ext_blob
return (ext, blob_id, int(getpipeoutput(['git cat-file blob %s' % blob_id, 'wc -l']).split()[0]))

class DataCollector:
class DataCollector(object):
"""Manages data collection from a revision control repository."""
def __init__(self):
self.stamp_created = time.time()
Expand Down Expand Up @@ -201,7 +202,7 @@ class DataCollector:
self.projectname = os.path.basename(os.path.abspath(dir))
else:
self.projectname = conf['project_name']

##
# Load cacheable data
def loadCache(self, cachefile):
Expand All @@ -216,7 +217,7 @@ class DataCollector:
f.seek(0)
self.cache = pickle.load(f)
f.close()

##
# Produce any additional statistics from the extracted data.
def refine(self):
Expand All @@ -226,7 +227,7 @@ class DataCollector:
# : get a dictionary of author
def getAuthorInfo(self, author):
return None

def getActivityByDayOfWeek(self):
return {}

Expand All @@ -241,31 +242,31 @@ class DataCollector:
# Get a list of authors
def getAuthors(self):
return []

def getFirstCommitDate(self):
return datetime.datetime.now()

def getLastCommitDate(self):
return datetime.datetime.now()

def getStampCreated(self):
return self.stamp_created

def getTags(self):
return []

def getTotalAuthors(self):
return -1

def getTotalCommits(self):
return -1

def getTotalFiles(self):
return -1

def getTotalLOC(self):
return -1

##
# Save cacheable data
def saveCache(self, cachefile):
Expand All @@ -283,10 +284,14 @@ class DataCollector:
os.rename(tempfile, cachefile)

class GitDataCollector(DataCollector):
def __init__(self):
super(GitDataCollector, self).__init__()
self.no_merges = "--no-merges" if conf["no_merges"] else ""

def collect(self, dir):
DataCollector.collect(self, dir)

self.total_authors += int(getpipeoutput(['git shortlog -s %s' % getlogrange(), 'wc -l']))
self.total_authors += int(getpipeoutput(['git shortlog -s %s %s' % (getlogrange(), self.no_merges), 'wc -l']))
#self.total_lines = int(getoutput('git-ls-files -z |xargs -0 cat |wc -l'))

# tags
Expand All @@ -311,7 +316,7 @@ class GitDataCollector(DataCollector):
tags_sorted_by_date_desc = map(lambda el : el[1], reversed(sorted(map(lambda el : (el[1]['date'], el[0]), self.tags.items()))))
prev = None
for tag in reversed(tags_sorted_by_date_desc):
cmd = 'git shortlog -s "%s"' % tag
cmd = 'git shortlog -s "%s" %s' % (tag, self.no_merges)
if prev != None:
cmd += ' "^%s"' % prev
output = getpipeoutput([cmd])
Expand All @@ -327,7 +332,7 @@ 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' % getlogrange('HEAD'), 'grep -v ^commit']).split('\n')
lines = getpipeoutput(['git rev-list --pretty=format:"%%at %%ai %%aN <%%aE>" %s %s' % (getlogrange('HEAD'), self.no_merges), 'grep -v ^commit']).split('\n')
for line in lines:
parts = line.split(' ', 4)
author = ''
Expand Down Expand Up @@ -434,7 +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' % getlogrange('HEAD'), 'grep -v ^commit']).strip().split('\n')
revlines = getpipeoutput(['git rev-list --pretty=format:"%%at %%T" %s %s' % (getlogrange('HEAD'), self.no_merges), 'grep -v ^commit']).strip().split('\n')
lines = []
revs_to_read = []
time_rev_count = []
Expand Down Expand Up @@ -536,7 +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, getlogrange('HEAD'))]).split('\n')
lines = getpipeoutput(['git log --shortstat %s --pretty=format:"%%at %%aN" %s %s' % (extra, getlogrange('HEAD'), self.no_merges)]).split('\n')
lines.reverse()
files = 0; inserted = 0; deleted = 0; total_lines = 0
author = None
Expand Down Expand Up @@ -590,7 +595,7 @@ 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' % (getlogrange('HEAD'))]).split('\n')
lines = getpipeoutput(['git log --shortstat --date-order --pretty=format:"%%at %%aN" %s %s' % (getlogrange('HEAD'), self.no_merges)]).split('\n')
lines.reverse()
files = 0; inserted = 0; deleted = 0
author = None
Expand Down Expand Up @@ -633,7 +638,7 @@ class GitDataCollector(DataCollector):
else:
print 'Warning: failed to handle line "%s"' % line
(files, inserted, deleted) = (0, 0, 0)

def refine(self):
# authors
# name -> {place_by_commits, commits_frac, date_first, date_last, timedelta}
Expand All @@ -653,7 +658,7 @@ class GitDataCollector(DataCollector):
a['timedelta'] = delta
if 'lines_added' not in a: a['lines_added'] = 0
if 'lines_removed' not in a: a['lines_removed'] = 0

def getActiveDays(self):
return self.active_days

Expand All @@ -665,12 +670,12 @@ class GitDataCollector(DataCollector):

def getAuthorInfo(self, author):
return self.authors[author]

def getAuthors(self, limit = None):
res = getkeyssortedbyvaluekey(self.authors, 'commits')
res.reverse()
return res[:limit]

def getCommitDeltaDays(self):
return (self.last_commit_stamp / 86400 - self.first_commit_stamp / 86400) + 1

Expand All @@ -679,44 +684,44 @@ class GitDataCollector(DataCollector):

def getDomains(self):
return self.domains.keys()

def getFirstCommitDate(self):
return datetime.datetime.fromtimestamp(self.first_commit_stamp)

def getLastCommitDate(self):
return datetime.datetime.fromtimestamp(self.last_commit_stamp)

def getTags(self):
lines = getpipeoutput(['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

def getTotalCommits(self):
return self.total_commits

def getTotalFiles(self):
return self.total_files

def getTotalLOC(self):
return self.total_lines

def getTotalSize(self):
return self.total_size

def revToDate(self, rev):
stamp = int(getpipeoutput(['git log --pretty=format:%%at "%s" -n 1' % rev]))
stamp = int(getpipeoutput(['git log --pretty=format:%%at "%s" -n 1 %s' % (rev, self.no_merges)]))
return datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d')

class ReportCreator:
"""Creates the actual report based on given data."""
def __init__(self):
pass

def create(self, data, path):
self.data = data
self.path = path
Expand Down Expand Up @@ -1094,7 +1099,7 @@ class HTMLReportCreator(ReportCreator):
#for stamp in sorted(data.files_by_stamp.keys()):
# fg.write('%s %d\n' % (datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), data.files_by_stamp[stamp]))
fg.close()

f.write('<img src="files_by_date.png" alt="Files by Date">')

#f.write('<h2>Average file size by date</h2>')
Expand Down Expand Up @@ -1166,7 +1171,7 @@ class HTMLReportCreator(ReportCreator):
f.close()

self.createGraphs(path)

def createGraphs(self, path):
print 'Generating graphs...'

Expand Down Expand Up @@ -1399,7 +1404,7 @@ plot """
</ul>
</div>
""")

def usage():
print """
Usage: gitstats [options] <gitpath..> <outputpath>
Expand Down