(Final Stage)

Upgrade to python 3
Make this a module (and installable)
Refactor single file into discrete files

gitstats/__init__.py

@@ -0,0 +1,11 @@
+from gitstats.gitstats import GitStats
+from gitstats._version import get_versions
+__version__ = get_versions()['version']
+del get_versions
+
+def main():
+    g = GitStats()
+    g.run()
+
+if __name__ == "__main__":
+    main()

gitstats/_version.py

@@ -0,0 +1,520 @@
+
+# This file helps to compute a version number in source trees obtained from
+# git-archive tarball (such as those provided by githubs download-from-tag
+# feature). Distribution tarballs (built by setup.py sdist) and build
+# directories (produced by setup.py build) will contain a much shorter file
+# that just contains the computed version number.
+
+# This file is released into the public domain. Generated by
+# versioneer-0.18 (https://github.com/warner/python-versioneer)
+
+"""Git implementation of _version.py."""
+
+import errno
+import os
+import re
+import subprocess
+import sys
+
+
+def get_keywords():
+    """Get the keywords needed to look up the version information."""
+    # these strings will be replaced by git during git-archive.
+    # setup.py/versioneer.py will grep for the variable names, so they must
+    # each be defined on a line of their own. _version.py will just call
+    # get_keywords().
+    git_refnames = "$Format:%d$"
+    git_full = "$Format:%H$"
+    git_date = "$Format:%ci$"
+    keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
+    return keywords
+
+
+class VersioneerConfig:
+    """Container for Versioneer configuration parameters."""
+
+
+def get_config():
+    """Create, populate and return the VersioneerConfig() object."""
+    # these strings are filled in when 'setup.py versioneer' creates
+    # _version.py
+    cfg = VersioneerConfig()
+    cfg.VCS = "git"
+    cfg.style = "pep440"
+    cfg.tag_prefix = ""
+    cfg.parentdir_prefix = "gitstats-"
+    cfg.versionfile_source = "gitstats/_version.py"
+    cfg.verbose = False
+    return cfg
+
+
+class NotThisMethod(Exception):
+    """Exception raised if a method is not valid for the current scenario."""
+
+
+LONG_VERSION_PY = {}
+HANDLERS = {}
+
+
+def register_vcs_handler(vcs, method):  # decorator
+    """Decorator to mark a method as the handler for a particular VCS."""
+    def decorate(f):
+        """Store f in HANDLERS[vcs][method]."""
+        if vcs not in HANDLERS:
+            HANDLERS[vcs] = {}
+        HANDLERS[vcs][method] = f
+        return f
+    return decorate
+
+
+def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False,
+                env=None):
+    """Call the given command(s)."""
+    assert isinstance(commands, list)
+    p = None
+    for c in commands:
+        try:
+            dispcmd = str([c] + args)
+            # remember shell=False, so use git.cmd on windows, not just git
+            p = subprocess.Popen([c] + args, cwd=cwd, env=env,
+                                 stdout=subprocess.PIPE,
+                                 stderr=(subprocess.PIPE if hide_stderr
+                                         else None))
+            break
+        except EnvironmentError:
+            e = sys.exc_info()[1]
+            if e.errno == errno.ENOENT:
+                continue
+            if verbose:
+                print("unable to run %s" % dispcmd)
+                print(e)
+            return None, None
+    else:
+        if verbose:
+            print("unable to find command, tried %s" % (commands,))
+        return None, None
+    stdout = p.communicate()[0].strip()
+    if sys.version_info[0] >= 3:
+        stdout = stdout.decode()
+    if p.returncode != 0:
+        if verbose:
+            print("unable to run %s (error)" % dispcmd)
+            print("stdout was %s" % stdout)
+        return None, p.returncode
+    return stdout, p.returncode
+
+
+def versions_from_parentdir(parentdir_prefix, root, verbose):
+    """Try to determine the version from the parent directory name.
+
+    Source tarballs conventionally unpack into a directory that includes both
+    the project name and a version string. We will also support searching up
+    two directory levels for an appropriately named parent directory
+    """
+    rootdirs = []
+
+    for i in range(3):
+        dirname = os.path.basename(root)
+        if dirname.startswith(parentdir_prefix):
+            return {"version": dirname[len(parentdir_prefix):],
+                    "full-revisionid": None,
+                    "dirty": False, "error": None, "date": None}
+        else:
+            rootdirs.append(root)
+            root = os.path.dirname(root)  # up a level
+
+    if verbose:
+        print("Tried directories %s but none started with prefix %s" %
+              (str(rootdirs), parentdir_prefix))
+    raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
+
+
+@register_vcs_handler("git", "get_keywords")
+def git_get_keywords(versionfile_abs):
+    """Extract version information from the given file."""
+    # the code embedded in _version.py can just fetch the value of these
+    # keywords. When used from setup.py, we don't want to import _version.py,
+    # so we do it with a regexp instead. This function is not used from
+    # _version.py.
+    keywords = {}
+    try:
+        f = open(versionfile_abs, "r")
+        for line in f.readlines():
+            if line.strip().startswith("git_refnames ="):
+                mo = re.search(r'=\s*"(.*)"', line)
+                if mo:
+                    keywords["refnames"] = mo.group(1)
+            if line.strip().startswith("git_full ="):
+                mo = re.search(r'=\s*"(.*)"', line)
+                if mo:
+                    keywords["full"] = mo.group(1)
+            if line.strip().startswith("git_date ="):
+                mo = re.search(r'=\s*"(.*)"', line)
+                if mo:
+                    keywords["date"] = mo.group(1)
+        f.close()
+    except EnvironmentError:
+        pass
+    return keywords
+
+
+@register_vcs_handler("git", "keywords")
+def git_versions_from_keywords(keywords, tag_prefix, verbose):
+    """Get version information from git keywords."""
+    if not keywords:
+        raise NotThisMethod("no keywords at all, weird")
+    date = keywords.get("date")
+    if date is not None:
+        # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant
+        # datestamp. However we prefer "%ci" (which expands to an "ISO-8601
+        # -like" string, which we must then edit to make compliant), because
+        # it's been around since git-1.5.3, and it's too difficult to
+        # discover which version we're using, or to work around using an
+        # older one.
+        date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
+    refnames = keywords["refnames"].strip()
+    if refnames.startswith("$Format"):
+        if verbose:
+            print("keywords are unexpanded, not using")
+        raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
+    refs = set([r.strip() for r in refnames.strip("()").split(",")])
+    # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
+    # just "foo-1.0". If we see a "tag: " prefix, prefer those.
+    TAG = "tag: "
+    tags = set([r[len(TAG):] for r in refs if r.startswith(TAG)])
+    if not tags:
+        # Either we're using git < 1.8.3, or there really are no tags. We use
+        # a heuristic: assume all version tags have a digit. The old git %d
+        # expansion behaves like git log --decorate=short and strips out the
+        # refs/heads/ and refs/tags/ prefixes that would let us distinguish
+        # between branches and tags. By ignoring refnames without digits, we
+        # filter out many common branch names like "release" and
+        # "stabilization", as well as "HEAD" and "master".
+        tags = set([r for r in refs if re.search(r'\d', r)])
+        if verbose:
+            print("discarding '%s', no digits" % ",".join(refs - tags))
+    if verbose:
+        print("likely tags: %s" % ",".join(sorted(tags)))
+    for ref in sorted(tags):
+        # sorting will prefer e.g. "2.0" over "2.0rc1"
+        if ref.startswith(tag_prefix):
+            r = ref[len(tag_prefix):]
+            if verbose:
+                print("picking %s" % r)
+            return {"version": r,
+                    "full-revisionid": keywords["full"].strip(),
+                    "dirty": False, "error": None,
+                    "date": date}
+    # no suitable tags, so version is "0+unknown", but full hex is still there
+    if verbose:
+        print("no suitable tags, using unknown + full revision id")
+    return {"version": "0+unknown",
+            "full-revisionid": keywords["full"].strip(),
+            "dirty": False, "error": "no suitable tags", "date": None}
+
+
+@register_vcs_handler("git", "pieces_from_vcs")
+def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
+    """Get version from 'git describe' in the root of the source tree.
+
+    This only gets called if the git-archive 'subst' keywords were *not*
+    expanded, and _version.py hasn't already been rewritten with a short
+    version string, meaning we're inside a checked out source tree.
+    """
+    GITS = ["git"]
+    if sys.platform == "win32":
+        GITS = ["git.cmd", "git.exe"]
+
+    out, rc = run_command(GITS, ["rev-parse", "--git-dir"], cwd=root,
+                          hide_stderr=True)
+    if rc != 0:
+        if verbose:
+            print("Directory %s not under git control" % root)
+        raise NotThisMethod("'git rev-parse --git-dir' returned error")
+
+    # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
+    # if there isn't one, this yields HEX[-dirty] (no NUM)
+    describe_out, rc = run_command(GITS, ["describe", "--tags", "--dirty",
+                                          "--always", "--long",
+                                          "--match", "%s*" % tag_prefix],
+                                   cwd=root)
+    # --long was added in git-1.5.5
+    if describe_out is None:
+        raise NotThisMethod("'git describe' failed")
+    describe_out = describe_out.strip()
+    full_out, rc = run_command(GITS, ["rev-parse", "HEAD"], cwd=root)
+    if full_out is None:
+        raise NotThisMethod("'git rev-parse' failed")
+    full_out = full_out.strip()
+
+    pieces = {}
+    pieces["long"] = full_out
+    pieces["short"] = full_out[:7]  # maybe improved later
+    pieces["error"] = None
+
+    # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty]
+    # TAG might have hyphens.
+    git_describe = describe_out
+
+    # look for -dirty suffix
+    dirty = git_describe.endswith("-dirty")
+    pieces["dirty"] = dirty
+    if dirty:
+        git_describe = git_describe[:git_describe.rindex("-dirty")]
+
+    # now we have TAG-NUM-gHEX or HEX
+
+    if "-" in git_describe:
+        # TAG-NUM-gHEX
+        mo = re.search(r'^(.+)-(\d+)-g([0-9a-f]+)$', git_describe)
+        if not mo:
+            # unparseable. Maybe git-describe is misbehaving?
+            pieces["error"] = ("unable to parse git-describe output: '%s'"
+                               % describe_out)
+            return pieces
+
+        # tag
+        full_tag = mo.group(1)
+        if not full_tag.startswith(tag_prefix):
+            if verbose:
+                fmt = "tag '%s' doesn't start with prefix '%s'"
+                print(fmt % (full_tag, tag_prefix))
+            pieces["error"] = ("tag '%s' doesn't start with prefix '%s'"
+                               % (full_tag, tag_prefix))
+            return pieces
+        pieces["closest-tag"] = full_tag[len(tag_prefix):]
+
+        # distance: number of commits since tag
+        pieces["distance"] = int(mo.group(2))
+
+        # commit: short hex revision ID
+        pieces["short"] = mo.group(3)
+
+    else:
+        # HEX: no tags
+        pieces["closest-tag"] = None
+        count_out, rc = run_command(GITS, ["rev-list", "HEAD", "--count"],
+                                    cwd=root)
+        pieces["distance"] = int(count_out)  # total number of commits
+
+    # commit date: see ISO-8601 comment in git_versions_from_keywords()
+    date = run_command(GITS, ["show", "-s", "--format=%ci", "HEAD"],
+                       cwd=root)[0].strip()
+    pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
+
+    return pieces
+
+
+def plus_or_dot(pieces):
+    """Return a + if we don't already have one, else return a ."""
+    if "+" in pieces.get("closest-tag", ""):
+        return "."
+    return "+"
+
+
+def render_pep440(pieces):
+    """Build up version string, with post-release "local version identifier".
+
+    Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you
+    get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty
+
+    Exceptions:
+    1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += plus_or_dot(pieces)
+            rendered += "%d.g%s" % (pieces["distance"], pieces["short"])
+            if pieces["dirty"]:
+                rendered += ".dirty"
+    else:
+        # exception #1
+        rendered = "0+untagged.%d.g%s" % (pieces["distance"],
+                                          pieces["short"])
+        if pieces["dirty"]:
+            rendered += ".dirty"
+    return rendered
+
+
+def render_pep440_pre(pieces):
+    """TAG[.post.devDISTANCE] -- No -dirty.
+
+    Exceptions:
+    1: no tags. 0.post.devDISTANCE
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"]:
+            rendered += ".post.dev%d" % pieces["distance"]
+    else:
+        # exception #1
+        rendered = "0.post.dev%d" % pieces["distance"]
+    return rendered
+
+
+def render_pep440_post(pieces):
+    """TAG[.postDISTANCE[.dev0]+gHEX] .
+
+    The ".dev0" means dirty. Note that .dev0 sorts backwards
+    (a dirty tree will appear "older" than the corresponding clean one),
+    but you shouldn't be releasing software with -dirty anyways.
+
+    Exceptions:
+    1: no tags. 0.postDISTANCE[.dev0]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += ".post%d" % pieces["distance"]
+            if pieces["dirty"]:
+                rendered += ".dev0"
+            rendered += plus_or_dot(pieces)
+            rendered += "g%s" % pieces["short"]
+    else:
+        # exception #1
+        rendered = "0.post%d" % pieces["distance"]
+        if pieces["dirty"]:
+            rendered += ".dev0"
+        rendered += "+g%s" % pieces["short"]
+    return rendered
+
+
+def render_pep440_old(pieces):
+    """TAG[.postDISTANCE[.dev0]] .
+
+    The ".dev0" means dirty.
+
+    Eexceptions:
+    1: no tags. 0.postDISTANCE[.dev0]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += ".post%d" % pieces["distance"]
+            if pieces["dirty"]:
+                rendered += ".dev0"
+    else:
+        # exception #1
+        rendered = "0.post%d" % pieces["distance"]
+        if pieces["dirty"]:
+            rendered += ".dev0"
+    return rendered
+
+
+def render_git_describe(pieces):
+    """TAG[-DISTANCE-gHEX][-dirty].
+
+    Like 'git describe --tags --dirty --always'.
+
+    Exceptions:
+    1: no tags. HEX[-dirty]  (note: no 'g' prefix)
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"]:
+            rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
+    else:
+        # exception #1
+        rendered = pieces["short"]
+    if pieces["dirty"]:
+        rendered += "-dirty"
+    return rendered
+
+
+def render_git_describe_long(pieces):
+    """TAG-DISTANCE-gHEX[-dirty].
+
+    Like 'git describe --tags --dirty --always -long'.
+    The distance/hash is unconditional.
+
+    Exceptions:
+    1: no tags. HEX[-dirty]  (note: no 'g' prefix)
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
+    else:
+        # exception #1
+        rendered = pieces["short"]
+    if pieces["dirty"]:
+        rendered += "-dirty"
+    return rendered
+
+
+def render(pieces, style):
+    """Render the given version pieces into the requested style."""
+    if pieces["error"]:
+        return {"version": "unknown",
+                "full-revisionid": pieces.get("long"),
+                "dirty": None,
+                "error": pieces["error"],
+                "date": None}
+
+    if not style or style == "default":
+        style = "pep440"  # the default
+
+    if style == "pep440":
+        rendered = render_pep440(pieces)
+    elif style == "pep440-pre":
+        rendered = render_pep440_pre(pieces)
+    elif style == "pep440-post":
+        rendered = render_pep440_post(pieces)
+    elif style == "pep440-old":
+        rendered = render_pep440_old(pieces)
+    elif style == "git-describe":
+        rendered = render_git_describe(pieces)
+    elif style == "git-describe-long":
+        rendered = render_git_describe_long(pieces)
+    else:
+        raise ValueError("unknown style '%s'" % style)
+
+    return {"version": rendered, "full-revisionid": pieces["long"],
+            "dirty": pieces["dirty"], "error": None,
+            "date": pieces.get("date")}
+
+
+def get_versions():
+    """Get version information or return default if unable to do so."""
+    # I am in _version.py, which lives at ROOT/VERSIONFILE_SOURCE. If we have
+    # __file__, we can work backwards from there to the root. Some
+    # py2exe/bbfreeze/non-CPython implementations don't do __file__, in which
+    # case we can only use expanded keywords.
+
+    cfg = get_config()
+    verbose = cfg.verbose
+
+    try:
+        return git_versions_from_keywords(get_keywords(), cfg.tag_prefix,
+                                          verbose)
+    except NotThisMethod:
+        pass
+
+    try:
+        root = os.path.realpath(__file__)
+        # versionfile_source is the relative path from the top of the source
+        # tree (where the .git directory might live) to this file. Invert
+        # this to find the root from __file__.
+        for i in cfg.versionfile_source.split('/'):
+            root = os.path.dirname(root)
+    except NameError:
+        return {"version": "0+unknown", "full-revisionid": None,
+                "dirty": None,
+                "error": "unable to find root of source tree",
+                "date": None}
+
+    try:
+        pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
+        return render(pieces, cfg.style)
+    except NotThisMethod:
+        pass
+
+    try:
+        if cfg.parentdir_prefix:
+            return versions_from_parentdir(cfg.parentdir_prefix, root, verbose)
+    except NotThisMethod:
+        pass
+
+    return {"version": "0+unknown", "full-revisionid": None,
+            "dirty": None,
+            "error": "unable to compute version", "date": None}

gitstats/datacollector.py

@@ -0,0 +1,157 @@
+import datetime
+import os
+import pickle
+import time
+import zlib
+
+
+class DataCollector:
+    """Manages data collection from a revision control repository."""
+
+    def __init__(self, conf):
+        self.conf = conf
+        self.stamp_created = time.time()
+        self.cache = {}
+        self.total_authors = 0
+        self.activity_by_hour_of_day = {}  # hour -> commits
+        self.activity_by_day_of_week = {}  # day -> commits
+        self.activity_by_month_of_year = {}  # month [1-12] -> commits
+        self.activity_by_hour_of_week = {}  # weekday -> hour -> commits
+        self.activity_by_hour_of_day_busiest = 0
+        self.activity_by_hour_of_week_busiest = 0
+        self.activity_by_year_week = {}  # yy_wNN -> commits
+        self.activity_by_year_week_peak = 0
+
+        self.authors = {}  # name -> {commits, first_commit_stamp, last_commit_stamp, last_active_day, active_days, lines_added, lines_removed}
+
+        self.total_commits = 0
+        self.total_files = 0
+        self.authors_by_commits = 0
+
+        # domains
+        self.domains = {}  # domain -> commits
+
+        # author of the month
+        self.author_of_month = {}  # month -> author -> commits
+        self.author_of_year = {}  # year -> author -> commits
+        self.commits_by_month = {}  # month -> commits
+        self.commits_by_year = {}  # year -> commits
+        self.lines_added_by_month = {}  # month -> lines added
+        self.lines_added_by_year = {}  # year -> lines added
+        self.lines_removed_by_month = {}  # month -> lines removed
+        self.lines_removed_by_year = {}  # year -> lines removed
+        self.first_commit_stamp = 0
+        self.last_commit_stamp = 0
+        self.last_active_day = None
+        self.active_days = set()
+
+        # lines
+        self.total_lines = 0
+        self.total_lines_added = 0
+        self.total_lines_removed = 0
+
+        # size
+        self.total_size = 0
+
+        # timezone
+        self.commits_by_timezone = {}  # timezone -> commits
+
+        # tags
+        self.tags = {}
+
+        self.files_by_stamp = {}  # stamp -> files
+
+        # extensions
+        self.extensions = {}  # extension -> files, lines
+
+        # line statistics
+        self.changes_by_date = {}  # stamp -> { files, ins, del }
+
+    ##
+    # This should be the main function to extract data from the repository.
+    def collect(self, dir):
+        self.dir = dir
+        if len(self.conf['project_name']) == 0:
+            self.projectname = os.path.basename(os.path.abspath(dir))
+        else:
+            self.projectname = self.conf['project_name']
+
+    ##
+    # Load cacheable data
+    def loadCache(self, cachefile):
+        if not os.path.exists(cachefile):
+            return
+        print('Loading cache...')
+        f = open(cachefile, 'rb')
+        try:
+            self.cache = pickle.loads(zlib.decompress(f.read()))
+        except:
+            # temporary hack to upgrade non-compressed caches
+            f.seek(0)
+            self.cache = pickle.load(f)
+        f.close()
+
+    ##
+    # Produce any additional statistics from the extracted data.
+    def refine(self):
+        pass
+
+    ##
+    # : get a dictionary of author
+    def getAuthorInfo(self, author):
+        return None
+
+    def getActivityByDayOfWeek(self):
+        return {}
+
+    def getActivityByHourOfDay(self):
+        return {}
+
+    # : get a dictionary of domains
+    def getDomainInfo(self, domain):
+        return None
+
+    ##
+    # 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):
+        print('Saving cache...')
+        tempfile = cachefile + '.tmp'
+        f = open(tempfile, 'wb')
+        # pickle.dump(self.cache, f)
+        data = zlib.compress(pickle.dumps(self.cache))
+        f.write(data)
+        f.close()
+        try:
+            os.remove(cachefile)
+        except OSError:
+            pass
+        os.rename(tempfile, cachefile)

gitstats/gitdatacollector.py

@@ -0,0 +1,452 @@
+import datetime
+import re
+import os
+
+from multiprocessing import Pool
+
+from .datacollector import DataCollector
+from .miscfuncs import getcommitrange, getkeyssortedbyvaluekey, getlogrange, getnumoffilesfromrev, getnumoflinesinblob, \
+    getpipeoutput, getstatsummarycounts
+
+
+class GitDataCollector(DataCollector):
+    def __init__(self, conf):
+        super(GitDataCollector, self).__init__(conf)
+        
+    def collect(self, directory):
+        super(GitDataCollector, self).collect(directory)
+
+        self.total_authors += int(getpipeoutput(['git shortlog -s %s' % getlogrange(self.conf), 'wc -l']))
+        # self.total_lines = int(getoutput('git-ls-files -z |xargs -0 cat |wc -l'))
+
+        # tags
+        lines = getpipeoutput(['git show-ref --tags']).split('\n')
+        for line in lines:
+            if len(line) == 0:
+                continue
+            (line_hash, tag) = line.split(' ')
+
+            tag = tag.replace('refs/tags/', '')
+            output = getpipeoutput(['git log "%s" --pretty=format:"%%at %%aN" -n 1' % line_hash])
+            if len(output) > 0:
+                parts = output.split(' ')
+                try:
+                    stamp = int(parts[0])
+                except ValueError:
+                    stamp = 0
+                self.tags[tag] = {'stamp': stamp, 'hash': line_hash,
+                                  'date': datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), 'commits': 0,
+                                  'authors': {}}
+
+        # collect info on tags, starting from latest
+        tags_sorted_by_date_asc = [tup[1] for tup in sorted([(el[1]['date'], el[0]) for el in self.tags.items()])]
+        # 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):
+        for tag in tags_sorted_by_date_asc:
+            cmd = 'git shortlog -s "%s"' % tag
+            if prev is not None:
+                cmd += ' "^%s"' % prev
+            output = getpipeoutput([cmd])
+            if len(output) == 0:
+                continue
+            prev = tag
+            for line in output.split('\n'):
+                parts = re.split('\s+', line, 2)
+                commits = int(parts[1])
+                author = parts[2]
+                self.tags[tag]['commits'] += commits
+                self.tags[tag]['authors'][author] = commits
+
+        # Collect revision statistics
+        # Outputs "<stamp> <date> <time> <timezone> <author> '<' <mail> '>'"
+        lines = getpipeoutput(
+            ['git rev-list --pretty=format:"%%at %%ai %%aN <%%aE>" %s' % getlogrange(self.conf, 'HEAD'), 'grep -v ^commit']).split(
+            '\n')
+        for line in lines:
+            parts = line.split(' ', 4)
+            try:
+                stamp = int(parts[0])
+            except ValueError:
+                stamp = 0
+            timezone = parts[3]
+            author, mail = parts[4].split('<', 1)
+            author = author.rstrip()
+            mail = mail.rstrip('>')
+            domain = '?'
+            if mail.find('@') != -1:
+                domain = mail.rsplit('@', 1)[1]
+            date = datetime.datetime.fromtimestamp(float(stamp))
+
+            # First and last commit stamp (may be in any order because of cherry-picking and patches)
+            if stamp > self.last_commit_stamp:
+                self.last_commit_stamp = stamp
+            if self.first_commit_stamp == 0 or stamp < self.first_commit_stamp:
+                self.first_commit_stamp = stamp
+
+            # activity
+            # hour
+            hour = date.hour
+            self.activity_by_hour_of_day[hour] = self.activity_by_hour_of_day.get(hour, 0) + 1
+            # most active hour?
+            if self.activity_by_hour_of_day[hour] > self.activity_by_hour_of_day_busiest:
+                self.activity_by_hour_of_day_busiest = self.activity_by_hour_of_day[hour]
+
+            # day of week
+            day = date.weekday()
+            self.activity_by_day_of_week[day] = self.activity_by_day_of_week.get(day, 0) + 1
+
+            # domain stats
+            if domain not in self.domains:
+                self.domains[domain] = {}
+            # commits
+            self.domains[domain]['commits'] = self.domains[domain].get('commits', 0) + 1
+
+            # hour of week
+            if day not in self.activity_by_hour_of_week:
+                self.activity_by_hour_of_week[day] = {}
+            self.activity_by_hour_of_week[day][hour] = self.activity_by_hour_of_week[day].get(hour, 0) + 1
+            # most active hour?
+            if self.activity_by_hour_of_week[day][hour] > self.activity_by_hour_of_week_busiest:
+                self.activity_by_hour_of_week_busiest = self.activity_by_hour_of_week[day][hour]
+
+            # month of year
+            month = date.month
+            self.activity_by_month_of_year[month] = self.activity_by_month_of_year.get(month, 0) + 1
+
+            # yearly/weekly activity
+            yyw = date.strftime('%Y-%W')
+            self.activity_by_year_week[yyw] = self.activity_by_year_week.get(yyw, 0) + 1
+            if self.activity_by_year_week_peak < self.activity_by_year_week[yyw]:
+                self.activity_by_year_week_peak = self.activity_by_year_week[yyw]
+
+            # author stats
+            if author not in self.authors:
+                self.authors[author] = {}
+            # commits, note again that commits may be in any date order because of cherry-picking and patches
+            if 'last_commit_stamp' not in self.authors[author]:
+                self.authors[author]['last_commit_stamp'] = stamp
+            if stamp > self.authors[author]['last_commit_stamp']:
+                self.authors[author]['last_commit_stamp'] = stamp
+            if 'first_commit_stamp' not in self.authors[author]:
+                self.authors[author]['first_commit_stamp'] = stamp
+            if stamp < self.authors[author]['first_commit_stamp']:
+                self.authors[author]['first_commit_stamp'] = stamp
+
+            # author of the month/year
+            yymm = date.strftime('%Y-%m')
+            if yymm in self.author_of_month:
+                self.author_of_month[yymm][author] = self.author_of_month[yymm].get(author, 0) + 1
+            else:
+                self.author_of_month[yymm] = {}
+                self.author_of_month[yymm][author] = 1
+            self.commits_by_month[yymm] = self.commits_by_month.get(yymm, 0) + 1
+
+            yy = date.year
+            if yy in self.author_of_year:
+                self.author_of_year[yy][author] = self.author_of_year[yy].get(author, 0) + 1
+            else:
+                self.author_of_year[yy] = {}
+                self.author_of_year[yy][author] = 1
+            self.commits_by_year[yy] = self.commits_by_year.get(yy, 0) + 1
+
+            # authors: active days
+            yymmdd = date.strftime('%Y-%m-%d')
+            if 'last_active_day' not in self.authors[author]:
+                self.authors[author]['last_active_day'] = yymmdd
+                self.authors[author]['active_days'] = {yymmdd}
+            elif yymmdd != self.authors[author]['last_active_day']:
+                self.authors[author]['last_active_day'] = yymmdd
+                self.authors[author]['active_days'].add(yymmdd)
+
+            # project: active days
+            if yymmdd != self.last_active_day:
+                self.last_active_day = yymmdd
+                self.active_days.add(yymmdd)
+
+            # timezone
+            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(self.conf, 'HEAD'), 'grep -v ^commit']).strip().split('\n')
+        lines = []
+        revs_to_read = []
+        # Look up rev in cache and take info from cache if found
+        # If not append rev to list of rev to read from repo
+        for revline in revlines:
+            time, rev = revline.split(' ')
+            # if cache empty then add time and rev to list of new rev's
+            # otherwise try to read needed info from cache
+            if 'files_in_tree' not in self.cache.keys():
+                revs_to_read.append((time, rev))
+                continue
+            if rev in self.cache['files_in_tree'].keys():
+                lines.append('%d %d' % (int(time), self.cache['files_in_tree'][rev]))
+            else:
+                revs_to_read.append((time, rev))
+
+        # Read revisions from repo
+        pool = Pool(processes=self.conf['processes'])
+        time_rev_count = pool.map(getnumoffilesfromrev, revs_to_read)
+        pool.terminate()
+        pool.join()
+
+        # Update cache with new revisions and append then to general list
+        for (time, rev, count) in time_rev_count:
+            if 'files_in_tree' not in self.cache:
+                self.cache['files_in_tree'] = {}
+            self.cache['files_in_tree'][rev] = count
+            lines.append('%d %d' % (int(time), count))
+
+        self.total_commits += len(lines)
+        for line in lines:
+            parts = line.split(' ')
+            if len(parts) != 2:
+                continue
+            (stamp, files) = parts[0:2]
+            try:
+                self.files_by_stamp[int(stamp)] = int(files)
+            except ValueError:
+                print(f'Warning: failed to parse line "{line}"')
+
+        # extensions and size of files
+        lines = getpipeoutput(['git ls-tree -r -l -z %s' % getcommitrange(self.conf, 'HEAD', end_only=True)]).split('\000')
+        blobs_to_read = []
+        for line in lines:
+            if len(line) == 0:
+                continue
+            parts = re.split('\s+', line, 4)
+            if parts[0] == '160000' and parts[3] == '-':
+                # skip submodules
+                continue
+            blob_id = parts[2]
+            size = int(parts[3])
+            fullpath = parts[4]
+
+            self.total_size += size
+            self.total_files += 1
+
+            _, ext = os.path.splitext(fullpath)
+            if len(ext) > self.conf['max_ext_length']:
+                ext = ''
+            if ext not in self.extensions:
+                self.extensions[ext] = {'files': 0, 'lines': 0}
+            self.extensions[ext]['files'] += 1
+            # if cache empty then add ext and blob id to list of new blob's
+            # otherwise try to read needed info from cache
+            if 'lines_in_blob' not in self.cache.keys():
+                blobs_to_read.append((ext, blob_id))
+                continue
+            if blob_id in self.cache['lines_in_blob'].keys():
+                self.extensions[ext]['lines'] += self.cache['lines_in_blob'][blob_id]
+            else:
+                blobs_to_read.append((ext, blob_id))
+
+        # Get info abount line count for new blob's that wasn't found in cache
+        pool = Pool(processes=self.conf['processes'])
+        ext_blob_linecount = pool.map(getnumoflinesinblob, blobs_to_read)
+        pool.terminate()
+        pool.join()
+
+        # Update cache and write down info about number of number of lines
+        for (ext, blob_id, linecount) in ext_blob_linecount:
+            if 'lines_in_blob' not in self.cache:
+                self.cache['lines_in_blob'] = {}
+            self.cache['lines_in_blob'][blob_id] = linecount
+            self.extensions[ext]['lines'] += self.cache['lines_in_blob'][blob_id]
+
+        # line statistics
+        # outputs:
+        #  N files changed, N insertions (+), N deletions(-)
+        # <stamp> <author>
+        self.changes_by_date = {}  # stamp -> { files, ins, del }
+        # computation of lines of code by date is better done
+        # on a linear history.
+        extra = ''
+        if self.conf['linear_linestats']:
+            extra = '--first-parent -m'
+        lines = getpipeoutput(
+            ['git log --shortstat %s --pretty=format:"%%at %%aN" %s' % (extra, getlogrange(self.conf, 'HEAD'))]).split('\n')
+        lines.reverse()
+        files = 0
+        inserted = 0
+        deleted = 0
+        total_lines = 0
+        for line in lines:
+            if len(line) == 0:
+                continue
+
+            # <stamp> <author>
+            if re.search('files? changed', line) is None:
+                pos = line.find(' ')
+                if pos != -1:
+                    try:
+                        (stamp, author) = (int(line[:pos]), line[pos + 1:])
+                        self.changes_by_date[stamp] = {'files': files, 'ins': inserted, 'del': deleted,
+                                                       'lines': total_lines}
+
+                        date = datetime.datetime.fromtimestamp(stamp)
+                        yymm = date.strftime('%Y-%m')
+                        self.lines_added_by_month[yymm] = self.lines_added_by_month.get(yymm, 0) + inserted
+                        self.lines_removed_by_month[yymm] = self.lines_removed_by_month.get(yymm, 0) + deleted
+
+                        yy = date.year
+                        self.lines_added_by_year[yy] = self.lines_added_by_year.get(yy, 0) + inserted
+                        self.lines_removed_by_year[yy] = self.lines_removed_by_year.get(yy, 0) + deleted
+
+                        files, inserted, deleted = 0, 0, 0
+                    except ValueError:
+                        print(f'Warning: unexpected line "{line}')
+                else:
+                    print(f'Warning: unexpected line "{line}')
+            else:
+                numbers = getstatsummarycounts(line)
+
+                if len(numbers) == 3:
+                    (files, inserted, deleted) = map(lambda el: int(el), numbers)
+                    total_lines += inserted
+                    total_lines -= deleted
+                    self.total_lines_added += inserted
+                    self.total_lines_removed += deleted
+
+                else:
+                    print(f'Warning: failed to handle line "{line}"')
+                    (files, inserted, deleted) = (0, 0, 0)
+            # self.changes_by_date[stamp] = { 'files': files, 'ins': inserted, 'del': deleted }
+        self.total_lines += total_lines
+
+        # Per-author statistics
+
+        # defined for stamp, author only if author commited at this timestamp.
+        self.changes_by_date_by_author = {}  # stamp -> author -> lines_added
+
+        # 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(self.conf, 'HEAD'))]).split('\n')
+        lines.reverse()
+        inserted = 0
+        deleted = 0
+        stamp = 0
+        for line in lines:
+            if len(line) == 0:
+                continue
+
+            # <stamp> <author>
+            if re.search('files? changed', line) is None:
+                pos = line.find(' ')
+                if pos != -1:
+                    try:
+                        oldstamp = stamp
+                        (stamp, author) = (int(line[:pos]), line[pos + 1:])
+                        if oldstamp > stamp:
+                            # clock skew, keep old timestamp to avoid having ugly graph
+                            stamp = oldstamp
+                        if author not in self.authors:
+                            self.authors[author] = {'lines_added': 0, 'lines_removed': 0, 'commits': 0}
+                        self.authors[author]['commits'] = self.authors[author].get('commits', 0) + 1
+                        self.authors[author]['lines_added'] = self.authors[author].get('lines_added', 0) + inserted
+                        self.authors[author]['lines_removed'] = self.authors[author].get('lines_removed', 0) + deleted
+                        if stamp not in self.changes_by_date_by_author:
+                            self.changes_by_date_by_author[stamp] = {}
+                        if author not in self.changes_by_date_by_author[stamp]:
+                            self.changes_by_date_by_author[stamp][author] = {}
+                        self.changes_by_date_by_author[stamp][author]['lines_added'] = self.authors[author][
+                            'lines_added']
+                        self.changes_by_date_by_author[stamp][author]['commits'] = self.authors[author]['commits']
+                        files, inserted, deleted = 0, 0, 0
+                    except ValueError:
+                        print(f'Warning: unexpected line "{line}')
+                else:
+                    print(f'Warning: unexpected line "{line}')
+            else:
+                numbers = getstatsummarycounts(line)
+
+                if len(numbers) == 3:
+                    (files, inserted, deleted) = map(lambda el: int(el), numbers)
+                else:
+                    print(f'Warning: failed to handle line "{line}"')
+                    (files, inserted, deleted) = (0, 0, 0)
+
+    def refine(self):
+        # authors
+        # name -> {place_by_commits, commits_frac, date_first, date_last, timedelta}
+        self.authors_by_commits = getkeyssortedbyvaluekey(self.authors, 'commits')
+        self.authors_by_commits.reverse()  # most first
+        for i, name in enumerate(self.authors_by_commits):
+            self.authors[name]['place_by_commits'] = i + 1
+
+        for name in self.authors.keys():
+            a = self.authors[name]
+            a['commits_frac'] = (100 * float(a['commits'])) / self.getTotalCommits()
+            date_first = datetime.datetime.fromtimestamp(a['first_commit_stamp'])
+            date_last = datetime.datetime.fromtimestamp(a['last_commit_stamp'])
+            delta = date_last - date_first
+            a['date_first'] = date_first.strftime('%Y-%m-%d')
+            a['date_last'] = date_last.strftime('%Y-%m-%d')
+            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
+
+    def getActivityByDayOfWeek(self):
+        return self.activity_by_day_of_week
+
+    def getActivityByHourOfDay(self):
+        return self.activity_by_hour_of_day
+
+    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
+
+    def getDomainInfo(self, domain):
+        return self.domains[domain]
+
+    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]))
+        return datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d')

gitstats/gitstats.py

@@ -0,0 +1,116 @@
+#!/usr/bin/python
+# Copyright (c) 2007-2014 Heikki Hokkanen <hoxu@users.sf.net> & others (see doc/AUTHOR)
+# GPLv2 / GPLv3
+import argparse
+import os
+import sys
+import time
+
+from .gitdatacollector import GitDataCollector
+from .htmlreportcreator import HTMLReportCreator
+from .miscfuncs import getgnuplotversion
+
+exectime_internal = 0.0
+exectime_external = 0.0
+
+conf = {
+    'max_domains': 10,
+    'max_ext_length': 10,
+    'style': 'gitstats.css',
+    'max_authors': 20,
+    'authors_top': 5,
+    'commit_begin': '',
+    'commit_end': 'HEAD',
+    'linear_linestats': 1,
+    'project_name': '',
+    'processes': 8,
+    'start_date': ''
+}
+
+class GitStats:
+    def _usage(self):
+        print(f"""
+    Usage: gitstats [options] <gitpath..> <outputpath>
+
+    Options:
+    -c key=value     Override configuration value
+
+    Default config values:
+    {conf}
+
+    Please see the manual page for more details.
+    """)
+
+    def run(self):
+        if len(sys.argv) < 2:
+            self._usage()
+            sys.exit(0)
+
+        parser = argparse.ArgumentParser(description='GitStats')
+#        parser.add_argument('-c', '--config', dest='config')
+
+        (args, remaining_args) = parser.parse_known_args()
+#        if args.config:
+#            self.conf.load(args.config)
+
+        time_start = time.time()
+
+        outputpath = remaining_args[-1]
+        paths = remaining_args[0:-1]
+        outputpath = os.path.abspath(outputpath)
+
+        rundir = os.getcwd()
+
+        try:
+            os.makedirs(outputpath)
+        except OSError:
+            pass
+        if not os.path.isdir(outputpath):
+            print('FATAL: Output path is not a directory or does not exist')
+            sys.exit(1)
+
+        if not getgnuplotversion():
+            print('gnuplot not found')
+            sys.exit(1)
+
+        print(f'Output path: {outputpath}')
+        cachefile = os.path.join(outputpath, 'gitstats.cache')
+
+        data = GitDataCollector(conf)
+        data.loadCache(cachefile)
+
+        for gitpath in paths:
+            print(f'Git path: {gitpath}')
+
+            prevdir = os.getcwd()
+            os.chdir(gitpath)
+
+            print('Collecting data...')
+            data.collect(gitpath)
+
+            os.chdir(prevdir)
+
+        print('Refining data...')
+        data.saveCache(cachefile)
+        data.refine()
+
+        os.chdir(rundir)
+
+        print('Generating report...')
+        report = HTMLReportCreator(conf)
+        report.create(data, outputpath)
+
+        time_end = time.time()
+        calculated_exectime_internal = time_end - time_start
+        print(
+            f'Execution time {calculated_exectime_internal} secs, {exectime_external} secs ({(100.0 * exectime_external) / calculated_exectime_internal}%) in external commands)')
+        if sys.stdin.isatty():
+            print('You may now run:')
+            print()
+            print('   sensible-browser \'%s\'' % os.path.join(outputpath, 'index.html').replace("'", "'\\''"))
+            print()
+
+
+if __name__ == '__main__':
+    g = GitStats()
+    g.run()

gitstats/htmlreportcreator.py

@@ -0,0 +1,733 @@
+import datetime
+import glob
+import pkg_resources
+import os
+import shutil
+import time
+
+from .reportcreator import ReportCreator
+from .miscfuncs import getgitversion, getgnuplotversion, getkeyssortedbyvaluekey, getkeyssortedbyvalues, getpipeoutput, \
+    getversion, gnuplot_cmd
+
+GNUPLOT_COMMON = 'set terminal png transparent size 640,240\nset size 1.0,1.0\n'
+WEEKDAYS = ('Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun')
+
+def html_linkify(text):
+    return text.lower().replace(' ', '_')
+
+
+def html_header(level, text):
+    name = html_linkify(text)
+    return '\n<h%d id="%s"><a href="#%s">%s</a></h%d>\n\n' % (level, name, name, text, level)
+
+
+class HTMLReportCreator(ReportCreator):
+    def __init(self, conf):
+        super(HTMLReportCreator, self).__init__(conf)
+
+    def create(self, data, path):
+        super(HTMLReportCreator, self).create(data, path)
+        self.title = data.projectname
+
+        # copy static files. Looks in the binary directory, ../share/gitstats and /usr/share/gitstats
+        resources = (self.conf['style'], 'sortable.js', 'arrow-up.gif', 'arrow-down.gif', 'arrow-none.gif')
+        for resource in (self.conf['style'], 'sortable.js', 'arrow-up.gif', 'arrow-down.gif', 'arrow-none.gif'):
+            resource_file = pkg_resources.resource_filename('gitstats', os.path.join('resources', resource))
+            if os.path.exists(resource_file):
+                shutil.copyfile(resource_file, os.path.join(path, resource))
+            else:
+                print(f'Warning: "{resource}" not found, so not copied')
+
+        f = open(path + "/index.html", 'w')
+        format = '%Y-%m-%d %H:%M:%S'
+        self.printHeader(f)
+
+        f.write('<h1>GitStats - %s</h1>' % data.projectname)
+
+        self.printNav(f)
+
+        f.write('<dl>')
+        f.write('<dt>Project name</dt><dd>%s</dd>' % (data.projectname))
+        f.write('<dt>Generated</dt><dd>%s (in %d seconds)</dd>' % (
+            datetime.datetime.now().strftime(format), time.time() - data.getStampCreated()))
+        f.write(
+            '<dt>Generator</dt><dd><a href="https://github.com/hoxu/gitstats">GitStats</a> (version %s), %s, %s</dd>' % (
+                getversion(), getgitversion(), getgnuplotversion()))
+        f.write('<dt>Report Period</dt><dd>%s to %s</dd>' % (
+            data.getFirstCommitDate().strftime(format), data.getLastCommitDate().strftime(format)))
+        f.write('<dt>Age</dt><dd>%d days, %d active days (%3.2f%%)</dd>' % (
+            data.getCommitDeltaDays(), len(data.getActiveDays()),
+            (100.0 * len(data.getActiveDays()) / data.getCommitDeltaDays())))
+        f.write('<dt>Total Files</dt><dd>%s</dd>' % data.getTotalFiles())
+        f.write('<dt>Total Lines of Code</dt><dd>%s (%d added, %d removed)</dd>' % (
+            data.getTotalLOC(), data.total_lines_added, data.total_lines_removed))
+        f.write('<dt>Total Commits</dt><dd>%s (average %.1f commits per active day, %.1f per all days)</dd>' % (
+            data.getTotalCommits(), float(data.getTotalCommits()) / len(data.getActiveDays()),
+            float(data.getTotalCommits()) / data.getCommitDeltaDays()))
+        f.write('<dt>Authors</dt><dd>%s (average %.1f commits per author)</dd>' % (
+            data.getTotalAuthors(), (1.0 * data.getTotalCommits()) / data.getTotalAuthors()))
+        f.write('</dl>')
+
+        f.write('</body>\n</html>')
+        f.close()
+
+        ###
+        # Activity
+        f = open(path + '/activity.html', 'w')
+        self.printHeader(f)
+        f.write('<h1>Activity</h1>')
+        self.printNav(f)
+
+        # f.write('<h2>Last 30 days</h2>')
+
+        # f.write('<h2>Last 12 months</h2>')
+
+        # Weekly activity
+        WEEKS = 32
+        f.write(html_header(2, 'Weekly activity'))
+        f.write('<p>Last %d weeks</p>' % WEEKS)
+
+        # generate weeks to show (previous N weeks from now)
+        now = datetime.datetime.now()
+        deltaweek = datetime.timedelta(7)
+        weeks = []
+        stampcur = now
+        for i in range(0, WEEKS):
+            weeks.insert(0, stampcur.strftime('%Y-%W'))
+            stampcur -= deltaweek
+
+        # top row: commits & bar
+        f.write('<table class="noborders"><tr>')
+        for i in range(0, WEEKS):
+            commits = 0
+            if weeks[i] in data.activity_by_year_week:
+                commits = data.activity_by_year_week[weeks[i]]
+
+            percentage = 0
+            if weeks[i] in data.activity_by_year_week:
+                percentage = float(data.activity_by_year_week[weeks[i]]) / data.activity_by_year_week_peak
+            height = max(1, int(200 * percentage))
+            f.write(
+                '<td style="text-align: center; vertical-align: bottom">%d<div style="display: block; background-color: red; width: 20px; height: %dpx"></div></td>' % (
+                    commits, height))
+
+        # bottom row: year/week
+        f.write('</tr><tr>')
+        for i in range(0, WEEKS):
+            f.write('<td>%s</td>' % (WEEKS - i))
+        f.write('</tr></table>')
+
+        # Hour of Day
+        f.write(html_header(2, 'Hour of Day'))
+        hour_of_day = data.getActivityByHourOfDay()
+        f.write('<table><tr><th>Hour</th>')
+        for i in range(0, 24):
+            f.write('<th>%d</th>' % i)
+        f.write('</tr>\n<tr><th>Commits</th>')
+        fp = open(path + '/hour_of_day.dat', 'w')
+        for i in range(0, 24):
+            if i in hour_of_day:
+                r = 127 + int((float(hour_of_day[i]) / data.activity_by_hour_of_day_busiest) * 128)
+                f.write('<td style="background-color: rgb(%d, 0, 0)">%d</td>' % (r, hour_of_day[i]))
+                fp.write('%d %d\n' % (i, hour_of_day[i]))
+            else:
+                f.write('<td>0</td>')
+                fp.write('%d 0\n' % i)
+        fp.close()
+        f.write('</tr>\n<tr><th>%</th>')
+        totalcommits = data.getTotalCommits()
+        for i in range(0, 24):
+            if i in hour_of_day:
+                r = 127 + int((float(hour_of_day[i]) / data.activity_by_hour_of_day_busiest) * 128)
+                f.write('<td style="background-color: rgb(%d, 0, 0)">%.2f</td>' % (
+                    r, (100.0 * hour_of_day[i]) / totalcommits))
+            else:
+                f.write('<td>0.00</td>')
+        f.write('</tr></table>')
+        f.write('<img src="hour_of_day.png" alt="Hour of Day">')
+        fg = open(path + '/hour_of_day.dat', 'w')
+        for i in range(0, 24):
+            if i in hour_of_day:
+                fg.write('%d %d\n' % (i + 1, hour_of_day[i]))
+            else:
+                fg.write('%d 0\n' % (i + 1))
+        fg.close()
+
+        # Day of Week
+        f.write(html_header(2, 'Day of Week'))
+        day_of_week = data.getActivityByDayOfWeek()
+        f.write('<div class="vtable"><table>')
+        f.write('<tr><th>Day</th><th>Total (%)</th></tr>')
+        fp = open(path + '/day_of_week.dat', 'w')
+        for d in range(0, 7):
+            commits = 0
+            if d in day_of_week:
+                commits = day_of_week[d]
+            fp.write('%d %s %d\n' % (d + 1, WEEKDAYS[d], commits))
+            f.write('<tr>')
+            f.write('<th>%s</th>' % (WEEKDAYS[d]))
+            if d in day_of_week:
+                f.write('<td>%d (%.2f%%)</td>' % (day_of_week[d], (100.0 * day_of_week[d]) / totalcommits))
+            else:
+                f.write('<td>0</td>')
+            f.write('</tr>')
+        f.write('</table></div>')
+        f.write('<img src="day_of_week.png" alt="Day of Week">')
+        fp.close()
+
+        # Hour of Week
+        f.write(html_header(2, 'Hour of Week'))
+        f.write('<table>')
+
+        f.write('<tr><th>Weekday</th>')
+        for hour in range(0, 24):
+            f.write('<th>%d</th>' % (hour))
+        f.write('</tr>')
+
+        for weekday in range(0, 7):
+            f.write('<tr><th>%s</th>' % (WEEKDAYS[weekday]))
+            for hour in range(0, 24):
+                try:
+                    commits = data.activity_by_hour_of_week[weekday][hour]
+                except KeyError:
+                    commits = 0
+                if commits != 0:
+                    f.write('<td')
+                    r = 127 + int((float(commits) / data.activity_by_hour_of_week_busiest) * 128)
+                    f.write(' style="background-color: rgb(%d, 0, 0)"' % r)
+                    f.write('>%d</td>' % commits)
+                else:
+                    f.write('<td></td>')
+            f.write('</tr>')
+
+        f.write('</table>')
+
+        # Month of Year
+        f.write(html_header(2, 'Month of Year'))
+        f.write('<div class="vtable"><table>')
+        f.write('<tr><th>Month</th><th>Commits (%)</th></tr>')
+        fp = open(path + '/month_of_year.dat', 'w')
+        for mm in range(1, 13):
+            commits = 0
+            if mm in data.activity_by_month_of_year:
+                commits = data.activity_by_month_of_year[mm]
+            f.write(
+                '<tr><td>%d</td><td>%d (%.2f %%)</td></tr>' % (mm, commits, (100.0 * commits) / data.getTotalCommits()))
+            fp.write('%d %d\n' % (mm, commits))
+        fp.close()
+        f.write('</table></div>')
+        f.write('<img src="month_of_year.png" alt="Month of Year">')
+
+        # Commits by year/month
+        f.write(html_header(2, 'Commits by year/month'))
+        f.write(
+            '<div class="vtable"><table><tr><th>Month</th><th>Commits</th><th>Lines added</th><th>Lines removed</th></tr>')
+        for yymm in reversed(sorted(data.commits_by_month.keys())):
+            f.write('<tr><td>%s</td><td>%d</td><td>%d</td><td>%d</td></tr>' % (
+                yymm, data.commits_by_month.get(yymm, 0), data.lines_added_by_month.get(yymm, 0),
+                data.lines_removed_by_month.get(yymm, 0)))
+        f.write('</table></div>')
+        f.write('<img src="commits_by_year_month.png" alt="Commits by year/month">')
+        fg = open(path + '/commits_by_year_month.dat', 'w')
+        for yymm in sorted(data.commits_by_month.keys()):
+            fg.write('%s %s\n' % (yymm, data.commits_by_month[yymm]))
+        fg.close()
+
+        # Commits by year
+        f.write(html_header(2, 'Commits by Year'))
+        f.write(
+            '<div class="vtable"><table><tr><th>Year</th><th>Commits (% of all)</th><th>Lines added</th><th>Lines removed</th></tr>')
+        for yy in reversed(sorted(data.commits_by_year.keys())):
+            f.write('<tr><td>%s</td><td>%d (%.2f%%)</td><td>%d</td><td>%d</td></tr>' % (
+                yy, data.commits_by_year.get(yy, 0), (100.0 * data.commits_by_year.get(yy, 0)) / data.getTotalCommits(),
+                data.lines_added_by_year.get(yy, 0), data.lines_removed_by_year.get(yy, 0)))
+        f.write('</table></div>')
+        f.write('<img src="commits_by_year.png" alt="Commits by Year">')
+        fg = open(path + '/commits_by_year.dat', 'w')
+        for yy in sorted(data.commits_by_year.keys()):
+            fg.write('%d %d\n' % (yy, data.commits_by_year[yy]))
+        fg.close()
+
+        # Commits by timezone
+        f.write(html_header(2, 'Commits by Timezone'))
+        f.write('<table><tr>')
+        f.write('<th>Timezone</th><th>Commits</th>')
+        f.write('</tr>')
+        max_commits_on_tz = max(data.commits_by_timezone.values())
+        for i in sorted(data.commits_by_timezone.keys(), key=lambda n: int(n)):
+            commits = data.commits_by_timezone[i]
+            r = 127 + int((float(commits) / max_commits_on_tz) * 128)
+            f.write('<tr><th>%s</th><td style="background-color: rgb(%d, 0, 0)">%d</td></tr>' % (i, r, commits))
+        f.write('</table>')
+
+        f.write('</body></html>')
+        f.close()
+
+        ###
+        # Authors
+        f = open(path + '/authors.html', 'w')
+        self.printHeader(f)
+
+        f.write('<h1>Authors</h1>')
+        self.printNav(f)
+
+        # Authors :: List of authors
+        f.write(html_header(2, 'List of Authors'))
+
+        f.write('<table class="authors sortable" id="authors">')
+        f.write(
+            '<tr><th>Author</th><th>Commits (%)</th><th>+ lines</th><th>- lines</th><th>First commit</th><th>Last commit</th><th class="unsortable">Age</th><th>Active days</th><th># by commits</th></tr>')
+        for author in data.getAuthors(self.conf['max_authors']):
+            info = data.getAuthorInfo(author)
+            f.write(
+                '<tr><td>%s</td><td>%d (%.2f%%)</td><td>%d</td><td>%d</td><td>%s</td><td>%s</td><td>%s</td><td>%d</td><td>%d</td></tr>' % (
+                    author, info['commits'], info['commits_frac'], info['lines_added'], info['lines_removed'],
+                    info['date_first'], info['date_last'], info['timedelta'], len(info['active_days']),
+                    info['place_by_commits']))
+        f.write('</table>')
+
+        allauthors = data.getAuthors()
+        if len(allauthors) > self.conf['max_authors']:
+            rest = allauthors[self.conf['max_authors']:]
+            f.write('<p class="moreauthors">These didn\'t make it to the top: %s</p>' % ', '.join(rest))
+
+        f.write(html_header(2, 'Cumulated Added Lines of Code per Author'))
+        f.write('<img src="lines_of_code_by_author.png" alt="Lines of code per Author">')
+        if len(allauthors) > self.conf['max_authors']:
+            f.write('<p class="moreauthors">Only top %d authors shown</p>' % self.conf['max_authors'])
+
+        f.write(html_header(2, 'Commits per Author'))
+        f.write('<img src="commits_by_author.png" alt="Commits per Author">')
+        if len(allauthors) > self.conf['max_authors']:
+            f.write('<p class="moreauthors">Only top %d authors shown</p>' % self.conf['max_authors'])
+
+        fgl = open(path + '/lines_of_code_by_author.dat', 'w')
+        fgc = open(path + '/commits_by_author.dat', 'w')
+
+        lines_by_authors = {}  # cumulated added lines by
+        # author. to save memory,
+        # changes_by_date_by_author[stamp][author] is defined
+        # only at points where author commits.
+        # lines_by_authors allows us to generate all the
+        # points in the .dat file.
+
+        # Don't rely on getAuthors to give the same order each
+        # time. Be robust and keep the list in a variable.
+        commits_by_authors = {}  # cumulated added lines by
+
+        self.authors_to_plot = data.getAuthors(self.conf['max_authors'])
+        for author in self.authors_to_plot:
+            lines_by_authors[author] = 0
+            commits_by_authors[author] = 0
+        for stamp in sorted(data.changes_by_date_by_author.keys()):
+            fgl.write('%d' % stamp)
+            fgc.write('%d' % stamp)
+            for author in self.authors_to_plot:
+                if author in data.changes_by_date_by_author[stamp].keys():
+                    lines_by_authors[author] = data.changes_by_date_by_author[stamp][author]['lines_added']
+                    commits_by_authors[author] = data.changes_by_date_by_author[stamp][author]['commits']
+                fgl.write(' %d' % lines_by_authors[author])
+                fgc.write(' %d' % commits_by_authors[author])
+            fgl.write('\n')
+            fgc.write('\n')
+        fgl.close()
+        fgc.close()
+
+        # Authors :: Author of Month
+        f.write(html_header(2, 'Author of Month'))
+        f.write('<table class="sortable" id="aom">')
+        f.write(
+            '<tr><th>Month</th><th>Author</th><th>Commits (%%)</th><th class="unsortable">Next top %d</th><th>Number of authors</th></tr>' %
+            self.conf['authors_top'])
+        for yymm in reversed(sorted(data.author_of_month.keys())):
+            authordict = data.author_of_month[yymm]
+            authors = getkeyssortedbyvalues(authordict)
+            authors.reverse()
+            commits = data.author_of_month[yymm][authors[0]]
+            next = ', '.join(authors[1:self.conf['authors_top'] + 1])
+            f.write('<tr><td>%s</td><td>%s</td><td>%d (%.2f%% of %d)</td><td>%s</td><td>%d</td></tr>' % (
+                yymm, authors[0], commits, (100.0 * commits) / data.commits_by_month[yymm], data.commits_by_month[yymm],
+                next, len(authors)))
+
+        f.write('</table>')
+
+        f.write(html_header(2, 'Author of Year'))
+        f.write(
+            '<table class="sortable" id="aoy"><tr><th>Year</th><th>Author</th><th>Commits (%%)</th><th class="unsortable">Next top %d</th><th>Number of authors</th></tr>' %
+            self.conf['authors_top'])
+        for yy in reversed(sorted(data.author_of_year.keys())):
+            authordict = data.author_of_year[yy]
+            authors = getkeyssortedbyvalues(authordict)
+            authors.reverse()
+            commits = data.author_of_year[yy][authors[0]]
+            next = ', '.join(authors[1:self.conf['authors_top'] + 1])
+            f.write('<tr><td>%s</td><td>%s</td><td>%d (%.2f%% of %d)</td><td>%s</td><td>%d</td></tr>' % (
+                yy, authors[0], commits, (100.0 * commits) / data.commits_by_year[yy], data.commits_by_year[yy], next,
+                len(authors)))
+        f.write('</table>')
+
+        # Domains
+        f.write(html_header(2, 'Commits by Domains'))
+        domains_by_commits = getkeyssortedbyvaluekey(data.domains, 'commits')
+        domains_by_commits.reverse()  # most first
+        f.write('<div class="vtable"><table>')
+        f.write('<tr><th>Domains</th><th>Total (%)</th></tr>')
+        fp = open(path + '/domains.dat', 'w')
+        n = 0
+        for domain in domains_by_commits:
+            if n == self.conf['max_domains']:
+                break
+            commits = 0
+            n += 1
+            info = data.getDomainInfo(domain)
+            fp.write('%s %d %d\n' % (domain, n, info['commits']))
+            f.write('<tr><th>%s</th><td>%d (%.2f%%)</td></tr>' % (
+                domain, info['commits'], (100.0 * info['commits'] / totalcommits)))
+        f.write('</table></div>')
+        f.write('<img src="domains.png" alt="Commits by Domains">')
+        fp.close()
+
+        f.write('</body></html>')
+        f.close()
+
+        ###
+        # Files
+        f = open(path + '/files.html', 'w')
+        self.printHeader(f)
+        f.write('<h1>Files</h1>')
+        self.printNav(f)
+
+        f.write('<dl>\n')
+        f.write('<dt>Total files</dt><dd>%d</dd>' % data.getTotalFiles())
+        f.write('<dt>Total lines</dt><dd>%d</dd>' % data.getTotalLOC())
+        try:
+            f.write(
+                '<dt>Average file size</dt><dd>%.2f bytes</dd>' % (float(data.getTotalSize()) / data.getTotalFiles()))
+        except ZeroDivisionError:
+            pass
+        f.write('</dl>\n')
+
+        # Files :: File count by date
+        f.write(html_header(2, 'File count by date'))
+
+        # use set to get rid of duplicate/unnecessary entries
+        files_by_date = set()
+        for stamp in sorted(data.files_by_stamp.keys()):
+            files_by_date.add(
+                '%s %d' % (datetime.datetime.fromtimestamp(stamp).strftime('%Y-%m-%d'), data.files_by_stamp[stamp]))
+
+        fg = open(path + '/files_by_date.dat', 'w')
+        for line in sorted(list(files_by_date)):
+            fg.write('%s\n' % line)
+        # 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>')
+
+        # Files :: Extensions
+        f.write(html_header(2, 'Extensions'))
+        f.write(
+            '<table class="sortable" id="ext"><tr><th>Extension</th><th>Files (%)</th><th>Lines (%)</th><th>Lines/file</th></tr>')
+        for ext in sorted(data.extensions.keys()):
+            files = data.extensions[ext]['files']
+            lines = data.extensions[ext]['lines']
+            try:
+                loc_percentage = (100.0 * lines) / data.getTotalLOC()
+            except ZeroDivisionError:
+                loc_percentage = 0
+            f.write('<tr><td>%s</td><td>%d (%.2f%%)</td><td>%d (%.2f%%)</td><td>%d</td></tr>' % (
+                ext, files, (100.0 * files) / data.getTotalFiles(), lines, loc_percentage, lines / files))
+        f.write('</table>')
+
+        f.write('</body></html>')
+        f.close()
+
+        ###
+        # Lines
+        f = open(path + '/lines.html', 'w')
+        self.printHeader(f)
+        f.write('<h1>Lines</h1>')
+        self.printNav(f)
+
+        f.write('<dl>\n')
+        f.write('<dt>Total lines</dt><dd>%d</dd>' % data.getTotalLOC())
+        f.write('</dl>\n')
+
+        f.write(html_header(2, 'Lines of Code'))
+        f.write('<img src="lines_of_code.png" alt="Lines of Code">')
+
+        fg = open(path + '/lines_of_code.dat', 'w')
+        for stamp in sorted(data.changes_by_date.keys()):
+            fg.write('%d %d\n' % (stamp, data.changes_by_date[stamp]['lines']))
+        fg.close()
+
+        f.write('</body></html>')
+        f.close()
+
+        ###
+        # tags.html
+        f = open(path + '/tags.html', 'w')
+        self.printHeader(f)
+        f.write('<h1>Tags</h1>')
+        self.printNav(f)
+
+        f.write('<dl>')
+        f.write('<dt>Total tags</dt><dd>%d</dd>' % len(data.tags))
+        if len(data.tags) > 0:
+            f.write('<dt>Average commits per tag</dt><dd>%.2f</dd>' % (1.0 * data.getTotalCommits() / len(data.tags)))
+        f.write('</dl>')
+
+        f.write('<table class="tags">')
+        f.write('<tr><th>Name</th><th>Date</th><th>Commits</th><th>Authors</th></tr>')
+        # sort the tags by date desc
+        tags_sorted_by_date_desc = map(lambda el: el[1],
+                                       reversed(sorted(map(lambda el: (el[1]['date'], el[0]), data.tags.items()))))
+        for tag in tags_sorted_by_date_desc:
+            authorinfo = []
+            self.authors_by_commits = getkeyssortedbyvalues(data.tags[tag]['authors'])
+            for i in reversed(self.authors_by_commits):
+                authorinfo.append('%s (%d)' % (i, data.tags[tag]['authors'][i]))
+            f.write('<tr><td>%s</td><td>%s</td><td>%d</td><td>%s</td></tr>' % (
+                tag, data.tags[tag]['date'], data.tags[tag]['commits'], ', '.join(authorinfo)))
+        f.write('</table>')
+
+        f.write('</body></html>')
+        f.close()
+
+        self.createGraphs(path)
+
+    def createGraphs(self, path):
+        print('Generating graphs...')
+
+        # hour of day
+        f = open(path + '/hour_of_day.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set output 'hour_of_day.png'
+            unset key
+            set xrange [0.5:24.5]
+            set yrange [0:]
+            set xtics 4
+            set grid y
+            set ylabel "Commits"
+            plot 'hour_of_day.dat' using 1:2:(0.5) w boxes fs solid
+            """)
+        f.close()
+
+        # day of week
+        f = open(path + '/day_of_week.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set output 'day_of_week.png'
+            unset key
+            set xrange [0.5:7.5]
+            set yrange [0:]
+            set xtics 1
+            set grid y
+            set ylabel "Commits"
+            plot 'day_of_week.dat' using 1:3:(0.5):xtic(2) w boxes fs solid
+            """)
+        f.close()
+
+        # Domains
+        f = open(path + '/domains.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set output 'domains.png'
+            unset key
+            unset xtics
+            set yrange [0:]
+            set grid y
+            set ylabel "Commits"
+            plot 'domains.dat' using 2:3:(0.5) with boxes fs solid, '' using 2:3:1 with labels rotate by 45 offset 0,1
+            """)
+        f.close()
+
+        # Month of Year
+        f = open(path + '/month_of_year.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set output 'month_of_year.png'
+            unset key
+            set xrange [0.5:12.5]
+            set yrange [0:]
+            set xtics 1
+            set grid y
+            set ylabel "Commits"
+            plot 'month_of_year.dat' using 1:2:(0.5) w boxes fs solid
+            """)
+        f.close()
+
+        # commits_by_year_month
+        f = open(path + '/commits_by_year_month.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set output 'commits_by_year_month.png'
+            unset key
+            set yrange [0:]
+            set xdata time
+            set timefmt "%Y-%m"
+            set format x "%Y-%m"
+            set xtics rotate
+            set bmargin 5
+            set grid y
+            set ylabel "Commits"
+            plot 'commits_by_year_month.dat' using 1:2:(0.5) w boxes fs solid
+            """)
+        f.close()
+
+        # commits_by_year
+        f = open(path + '/commits_by_year.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set output 'commits_by_year.png'
+            unset key
+            set yrange [0:]
+            set xtics 1 rotate
+            set grid y
+            set ylabel "Commits"
+            set yrange [0:]
+            plot 'commits_by_year.dat' using 1:2:(0.5) w boxes fs solid
+            """)
+        f.close()
+
+        # Files by date
+        f = open(path + '/files_by_date.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set output 'files_by_date.png'
+            unset key
+            set yrange [0:]
+            set xdata time
+            set timefmt "%Y-%m-%d"
+            set format x "%Y-%m-%d"
+            set grid y
+            set ylabel "Files"
+            set xtics rotate
+            set ytics autofreq
+            set bmargin 6
+            plot 'files_by_date.dat' using 1:2 w steps
+            """)
+        f.close()
+
+        # Lines of Code
+        f = open(path + '/lines_of_code.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set output 'lines_of_code.png'
+            unset key
+            set yrange [0:]
+            set xdata time
+            set timefmt "%s"
+            set format x "%Y-%m-%d"
+            set grid y
+            set ylabel "Lines"
+            set xtics rotate
+            set bmargin 6
+            plot 'lines_of_code.dat' using 1:2 w lines
+            """)
+        f.close()
+
+        # Lines of Code Added per author
+        f = open(path + '/lines_of_code_by_author.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set terminal png transparent size 640,480
+            set output 'lines_of_code_by_author.png'
+            set key left top
+            set yrange [0:]
+            set xdata time
+            set timefmt "%s"
+            set format x "%Y-%m-%d"
+            set grid y
+            set ylabel "Lines"
+            set xtics rotate
+            set bmargin 6
+            plot """
+        )
+        i = 1
+        plots = []
+        for a in self.authors_to_plot:
+            i = i + 1
+            author = a.replace("\"", "\\\"").replace("`", "")
+            plots.append("""'lines_of_code_by_author.dat' using 1:%d title "%s" w lines""" % (i, author))
+        f.write(", ".join(plots))
+        f.write('\n')
+
+        f.close()
+
+        # Commits per author
+        f = open(path + '/commits_by_author.plot', 'w')
+        f.write(GNUPLOT_COMMON)
+        f.write(
+            """
+            set terminal png transparent size 640,480
+            set output 'commits_by_author.png'
+            set key left top
+            set yrange [0:]
+            set xdata time
+            set timefmt "%s"
+            set format x "%Y-%m-%d"
+            set grid y
+            set ylabel "Commits"
+            set xtics rotate
+            set bmargin 6
+            plot """
+        )
+        i = 1
+        plots = []
+        for a in self.authors_to_plot:
+            i = i + 1
+            author = a.replace("\"", "\\\"").replace("`", "")
+            plots.append("""'commits_by_author.dat' using 1:%d title "%s" w lines""" % (i, author))
+        f.write(", ".join(plots))
+        f.write('\n')
+
+        f.close()
+
+        os.chdir(path)
+        files = glob.glob(path + '/*.plot')
+        for f in files:
+            out = getpipeoutput([gnuplot_cmd + ' "%s"' % f])
+            if len(out) > 0:
+                print(out)
+
+    def printHeader(self, f, title=''):
+        f.write(
+            """<!DOCTYPE html>
+            <html>
+            <head>
+                <meta charset="UTF-8">
+                <title>GitStats - %s</title>
+                <link rel="stylesheet" href="%s" type="text/css">
+                <meta name="generator" content="GitStats %s">
+                <script type="text/javascript" src="sortable.js"></script>
+            </head>
+            <body>
+            """ % (self.title, self.conf['style'], getversion()))
+
+    def printNav(self, f):
+        f.write("""
+<div class="nav">
+<ul>
+<li><a href="index.html">General</a></li>
+<li><a href="activity.html">Activity</a></li>
+<li><a href="authors.html">Authors</a></li>
+<li><a href="files.html">Files</a></li>
+<li><a href="lines.html">Lines</a></li>
+<li><a href="tags.html">Tags</a></li>
+</ul>
+</div>
+""")

gitstats/miscfuncs.py

@@ -0,0 +1,105 @@
+import os
+import platform
+import re
+import subprocess
+import sys
+import time
+
+os.environ['LC_ALL'] = 'C'
+
+ON_LINUX = (platform.system() == 'Linux')
+
+# By default, gnuplot is searched from path, but can be overridden with the
+# environment variable "GNUPLOT"
+gnuplot_cmd = 'gnuplot'
+if 'GNUPLOT' in os.environ:
+    gnuplot_cmd = os.environ['GNUPLOT']
+
+
+def getpipeoutput(cmds, quiet=False):
+    start = time.time()
+    if not quiet and ON_LINUX and os.isatty(1):
+        print('>> ' + ' | '.join(cmds), sys.stdout.flush())
+    p = subprocess.Popen(cmds[0], stdout=subprocess.PIPE, shell=True)
+    processes = [p]
+    for x in cmds[1:]:
+        p = subprocess.Popen(x, stdin=p.stdout, stdout=subprocess.PIPE, shell=True)
+        processes.append(p)
+    output = p.communicate()[0].decode('utf-8')
+    for p in processes:
+        p.wait()
+    end = time.time()
+    if not quiet:
+        if ON_LINUX and os.isatty(1):
+            print(f'\r[{end - start}] >> {" | ".join(cmds)}')
+    return output.rstrip('\n')
+
+
+def getlogrange(conf, defaultrange='HEAD', end_only=True):
+    commit_range = getcommitrange(conf, defaultrange, end_only)
+    if len(conf['start_date']) > 0:
+        return '--since="%s" "%s"' % (conf['start_date'], commit_range)
+    return commit_range
+
+
+def getcommitrange(conf, defaultrange='HEAD', end_only=False):
+    if len(conf['commit_end']) > 0:
+        if end_only or len(conf['commit_begin']) == 0:
+            return conf['commit_end']
+        return '%s..%s' % (conf['commit_begin'], conf['commit_end'])
+    return defaultrange
+
+
+def getkeyssortedbyvalues(dictionary):
+    return [elem[1] for elem in sorted([(el[1], el[0]) for el in dictionary.items()])]
+
+
+# dict['author'] = { 'commits': 512 } - ...key(dict, 'commits')
+def getkeyssortedbyvaluekey(d, key):
+    return [elem[1] for elem in sorted([(d[el][key], el) for el in d.keys()])]
+
+
+def getstatsummarycounts(line):
+    numbers = re.findall('\d+', line)
+    if len(numbers) == 1:
+        # neither insertions nor deletions: may probably only happen for "0 files changed"
+        numbers.append(0)
+        numbers.append(0)
+    elif len(numbers) == 2 and line.find('(+)') != -1:
+        numbers.append(0)  # only insertions were printed on line
+    elif len(numbers) == 2 and line.find('(-)') != -1:
+        numbers.insert(1, 0)  # only deletions were printed on line
+    return numbers
+
+
+def getversion():
+    from ._version import get_versions
+    __version__ = get_versions()['version']
+    del get_versions
+    return __version__
+
+
+def getgitversion():
+    return getpipeoutput(['git --version']).split('\n')[0]
+
+
+def getgnuplotversion():
+    return getpipeoutput(['%s --version' % gnuplot_cmd]).split('\n')[0]
+
+
+def getnumoffilesfromrev(time_rev):
+    """
+    Get number of files changed in commit
+    """
+    time_portion, rev = time_rev
+    return (int(time_portion), rev, int(getpipeoutput(['git ls-tree -r --name-only "%s"' % rev, 'wc -l']).split('\n')[0]))
+
+
+def getnumoflinesinblob(ext_blob):
+    """
+    Get number of lines in blob
+    """
+    ext, blob_id = ext_blob
+    return ext, blob_id, int(getpipeoutput(['git cat-file blob %s' % blob_id, 'wc -l']).split()[0])
+
+

gitstats/reportcreator.py

@@ -0,0 +1,11 @@
+class ReportCreator:
+    """Creates the actual report based on given data."""
+
+    def __init__(self, conf):
+        self.conf = conf
+        self.data = None
+        self.path = None
+
+    def create(self, data, path):
+        self.data = data
+        self.path = path

gitstats/resources/gitstats.css

@@ -0,0 +1,145 @@
+/**
+ * GitStats - default style
+ */
+body {
+	color: black;
+	background-color: #dfd;
+}
+
+dt {
+	font-weight: bold;
+	float: left;
+	margin-right: 1em;
+}
+
+dt:after {
+	content: ': ';
+}
+
+dd {
+	display: block;
+	clear: left;
+}
+
+table {
+	border: 1px solid black;
+	border-collapse: collapse;
+	font-size: 80%;
+	margin-bottom: 1em;
+}
+
+table.noborders {
+	border: none;
+}
+
+table.noborders td {
+	border: none;
+}
+
+.vtable {
+	float: right;
+	clear: both;
+}
+
+table.tags td {
+	vertical-align: top;
+}
+
+td {
+	background-color: white;
+}
+
+th {
+	background-color: #ddf;
+}
+
+th a {
+	text-decoration: none;
+}
+
+tr:hover {
+	background-color: #ddf;
+}
+
+td {
+	border: 1px solid black;
+	padding: 0.2em;
+	padding-left: 0.3em;
+	padding-right: 0.2em;
+}
+
+/* Navigation bar; tabbed style */
+.nav {
+	border-bottom: 1px solid black;
+	padding: 0.3em;
+}
+
+.nav ul {
+	list-style-type: none;
+	display: inline;
+	margin: 0;
+	padding: 0;
+}
+
+.nav li {
+	display: inline;
+}
+
+.nav li a {
+	padding: 0.3em;
+	text-decoration: none;
+	color: black;
+	border: 1px solid black;
+	margin: 0.5em;
+	background-color: #ddf;
+}
+
+.nav li a:hover {
+	background-color: #ddd;
+	border-bottom: 1px solid #ddf;
+}
+
+img {
+	border: 1px solid black;
+	padding: 0.5em;
+	background-color: white;
+}
+
+th img {
+	border: 0px;
+	padding: 0px;
+	background-color: #ddf;
+}
+
+h1 a, h2 a {
+	color: black;
+	text-decoration: none;
+}
+
+h1:hover a:after,
+h2:hover a:after {
+	content: '¶';
+	color: #555;
+}
+
+h1 {
+	font-size: x-large;
+}
+
+h2 {
+	background-color: #564;
+	border: 1px solid black;
+	padding-left: 0.5em;
+	padding-right: 0.5em;
+	color: white;
+	font-size: large;
+	clear: both;
+}
+
+h2 a {
+	color: white;
+}
+
+.moreauthors {
+	font-size: 80%;
+}

gitstats/resources/sortable.js

@@ -0,0 +1,324 @@
+/*
+Table sorting script  by Joost de Valk, check it out at http://www.joostdevalk.nl/code/sortable-table/.
+Based on a script from http://www.kryogenix.org/code/browser/sorttable/.
+Distributed under the MIT license: http://www.kryogenix.org/code/browser/licence.html .
+
+Copyright (c) 1997-2007 Stuart Langridge, Joost de Valk.
+
+Version 1.5.7
+*/
+
+/* You can change these values */
+var image_path = "";
+var image_up = "arrow-up.gif";
+var image_down = "arrow-down.gif";
+var image_none = "arrow-none.gif";
+var europeandate = true;
+var alternate_row_colors = true;
+
+/* Don't change anything below this unless you know what you're doing */
+addEvent(window, "load", sortables_init);
+
+var SORT_COLUMN_INDEX;
+var thead = false;
+
+function sortables_init() {
+	// Find all tables with class sortable and make them sortable
+	if (!document.getElementsByTagName) return;
+	tbls = document.getElementsByTagName("table");
+	for (ti=0;ti<tbls.length;ti++) {
+		thisTbl = tbls[ti];
+		if (((' '+thisTbl.className+' ').indexOf("sortable") != -1) && (thisTbl.id)) {
+			ts_makeSortable(thisTbl);
+		}
+	}
+}
+
+function ts_makeSortable(t) {
+	if (t.rows && t.rows.length > 0) {
+		if (t.tHead && t.tHead.rows.length > 0) {
+			var firstRow = t.tHead.rows[t.tHead.rows.length-1];
+			thead = true;
+		} else {
+			var firstRow = t.rows[0];
+		}
+	}
+	if (!firstRow) return;
+	
+	// We have a first row: assume it's the header, and make its contents clickable links
+	for (var i=0;i<firstRow.cells.length;i++) {
+		var cell = firstRow.cells[i];
+		var txt = ts_getInnerText(cell);
+		if (cell.className != "unsortable" && cell.className.indexOf("unsortable") == -1) {
+			cell.innerHTML = '<a href="#" class="sortheader" onclick="ts_resortTable(this, '+i+');return false;">'+txt+'<span class="sortarrow">&nbsp;&nbsp;<img src="'+ image_path + image_none + '" alt="&darr;"/></span></a>';
+		}
+	}
+	if (alternate_row_colors) {
+		alternate(t);
+	}
+}
+
+function ts_getInnerText(el) {
+	if (typeof el == "string") return el;
+	if (typeof el == "undefined") { return el };
+	if (el.innerText) return el.innerText;	//Not needed but it is faster
+	var str = "";
+	
+	var cs = el.childNodes;
+	var l = cs.length;
+	for (var i = 0; i < l; i++) {
+		switch (cs[i].nodeType) {
+			case 1: //ELEMENT_NODE
+				str += ts_getInnerText(cs[i]);
+				break;
+			case 3:	//TEXT_NODE
+				str += cs[i].nodeValue;
+				break;
+		}
+	}
+	return str;
+}
+
+function ts_resortTable(lnk, clid) {
+	var span;
+	for (var ci=0;ci<lnk.childNodes.length;ci++) {
+		if (lnk.childNodes[ci].tagName && lnk.childNodes[ci].tagName.toLowerCase() == 'span') span = lnk.childNodes[ci];
+	}
+	var spantext = ts_getInnerText(span);
+	var td = lnk.parentNode;
+	var column = clid || td.cellIndex;
+	var t = getParent(td,'TABLE');
+	// Work out a type for the column
+	if (t.rows.length <= 1) return;
+	var itm = "";
+	var i = 1;
+	while (itm == "" && i < t.tBodies[0].rows.length) {
+		var itm = ts_getInnerText(t.tBodies[0].rows[i].cells[column]);
+		itm = trim(itm);
+		if (itm.substr(0,4) == "<!--" || itm.length == 0) {
+			itm = "";
+		}
+		i++;
+	}
+	if (itm == "") return; 
+	sortfn = ts_sort_caseinsensitive;
+	if (itm.match(/^\d\d[\/\.-][a-zA-z][a-zA-Z][a-zA-Z][\/\.-]\d\d\d\d$/)) sortfn = ts_sort_date;
+	if (itm.match(/^\d\d[\/\.-]\d\d[\/\.-]\d\d\d{2}?$/)) sortfn = ts_sort_date;
+	if (itm.match(/^-?[£$€Û¢´]\d/)) sortfn = ts_sort_numeric;
+	// ignore stuff in () after the numbers.
+	if (itm.match(/^-?(\d+[,\.]?)+(E[-+][\d]+)?%?( \(.*\))?$/)) sortfn = ts_sort_numeric;
+	SORT_COLUMN_INDEX = column;
+	var firstRow = new Array();
+	var newRows = new Array();
+	for (k=0;k<t.tBodies.length;k++) {
+		for (i=0;i<t.tBodies[k].rows[0].length;i++) { 
+			firstRow[i] = t.tBodies[k].rows[0][i]; 
+		}
+	}
+	for (k=0;k<t.tBodies.length;k++) {
+		if (!thead) {
+			// Skip the first row
+			for (j=1;j<t.tBodies[k].rows.length;j++) { 
+				newRows[j-1] = t.tBodies[k].rows[j];
+			}
+		} else {
+			// Do NOT skip the first row
+			for (j=0;j<t.tBodies[k].rows.length;j++) { 
+				newRows[j] = t.tBodies[k].rows[j];
+			}
+		}
+	}
+	newRows.sort(sortfn);
+	if (span.getAttribute("sortdir") == 'down') {
+			ARROW = '&nbsp;&nbsp;<img src="'+ image_path + image_down + '" alt="&darr;"/>';
+			newRows.reverse();
+			span.setAttribute('sortdir','up');
+	} else {
+			ARROW = '&nbsp;&nbsp;<img src="'+ image_path + image_up + '" alt="&uarr;"/>';
+			span.setAttribute('sortdir','down');
+	} 
+    // We appendChild rows that already exist to the tbody, so it moves them rather than creating new ones
+    // don't do sortbottom rows
+    for (i=0; i<newRows.length; i++) { 
+		if (!newRows[i].className || (newRows[i].className && (newRows[i].className.indexOf('sortbottom') == -1))) {
+			t.tBodies[0].appendChild(newRows[i]);
+		}
+	}
+    // do sortbottom rows only
+    for (i=0; i<newRows.length; i++) {
+		if (newRows[i].className && (newRows[i].className.indexOf('sortbottom') != -1)) 
+			t.tBodies[0].appendChild(newRows[i]);
+	}
+	// Delete any other arrows there may be showing
+	var allspans = document.getElementsByTagName("span");
+	for (var ci=0;ci<allspans.length;ci++) {
+		if (allspans[ci].className == 'sortarrow') {
+			if (getParent(allspans[ci],"table") == getParent(lnk,"table")) { // in the same table as us?
+				allspans[ci].innerHTML = '&nbsp;&nbsp;<img src="'+ image_path + image_none + '" alt="&darr;"/>';
+			}
+		}
+	}		
+	span.innerHTML = ARROW;
+	alternate(t);
+}
+
+function getParent(el, pTagName) {
+	if (el == null) {
+		return null;
+	} else if (el.nodeType == 1 && el.tagName.toLowerCase() == pTagName.toLowerCase()) {
+		return el;
+	} else {
+		return getParent(el.parentNode, pTagName);
+	}
+}
+
+function sort_date(date) {	
+	// y2k notes: two digit years less than 50 are treated as 20XX, greater than 50 are treated as 19XX
+	dt = "00000000";
+	if (date.length == 11) {
+		mtstr = date.substr(3,3);
+		mtstr = mtstr.toLowerCase();
+		switch(mtstr) {
+			case "jan": var mt = "01"; break;
+			case "feb": var mt = "02"; break;
+			case "mar": var mt = "03"; break;
+			case "apr": var mt = "04"; break;
+			case "may": var mt = "05"; break;
+			case "jun": var mt = "06"; break;
+			case "jul": var mt = "07"; break;
+			case "aug": var mt = "08"; break;
+			case "sep": var mt = "09"; break;
+			case "oct": var mt = "10"; break;
+			case "nov": var mt = "11"; break;
+			case "dec": var mt = "12"; break;
+			// default: var mt = "00";
+		}
+		dt = date.substr(7,4)+mt+date.substr(0,2);
+		return dt;
+	} else if (date.length == 10) {
+		if (europeandate == false) {
+			dt = date.substr(6,4)+date.substr(0,2)+date.substr(3,2);
+			return dt;
+		} else {
+			dt = date.substr(6,4)+date.substr(3,2)+date.substr(0,2);
+			return dt;
+		}
+	} else if (date.length == 8) {
+		yr = date.substr(6,2);
+		if (parseInt(yr) < 50) { 
+			yr = '20'+yr; 
+		} else { 
+			yr = '19'+yr; 
+		}
+		if (europeandate == true) {
+			dt = yr+date.substr(3,2)+date.substr(0,2);
+			return dt;
+		} else {
+			dt = yr+date.substr(0,2)+date.substr(3,2);
+			return dt;
+		}
+	}
+	return dt;
+}
+
+function ts_sort_date(a,b) {
+	dt1 = sort_date(ts_getInnerText(a.cells[SORT_COLUMN_INDEX]));
+	dt2 = sort_date(ts_getInnerText(b.cells[SORT_COLUMN_INDEX]));
+	
+	if (dt1==dt2) {
+		return 0;
+	}
+	if (dt1<dt2) { 
+		return -1;
+	}
+	return 1;
+}
+function ts_sort_numeric(a,b) {
+	var aa = ts_getInnerText(a.cells[SORT_COLUMN_INDEX]);
+	aa = clean_num(aa);
+	var bb = ts_getInnerText(b.cells[SORT_COLUMN_INDEX]);
+	bb = clean_num(bb);
+	return compare_numeric(aa,bb);
+}
+function compare_numeric(a,b) {
+	var a = parseFloat(a);
+	a = (isNaN(a) ? 0 : a);
+	var b = parseFloat(b);
+	b = (isNaN(b) ? 0 : b);
+	return a - b;
+}
+function ts_sort_caseinsensitive(a,b) {
+	aa = ts_getInnerText(a.cells[SORT_COLUMN_INDEX]).toLowerCase();
+	bb = ts_getInnerText(b.cells[SORT_COLUMN_INDEX]).toLowerCase();
+	if (aa==bb) {
+		return 0;
+	}
+	if (aa<bb) {
+		return -1;
+	}
+	return 1;
+}
+function ts_sort_default(a,b) {
+	aa = ts_getInnerText(a.cells[SORT_COLUMN_INDEX]);
+	bb = ts_getInnerText(b.cells[SORT_COLUMN_INDEX]);
+	if (aa==bb) {
+		return 0;
+	}
+	if (aa<bb) {
+		return -1;
+	}
+	return 1;
+}
+function addEvent(elm, evType, fn, useCapture)
+// addEvent and removeEvent
+// cross-browser event handling for IE5+,	NS6 and Mozilla
+// By Scott Andrew
+{
+	if (elm.addEventListener){
+		elm.addEventListener(evType, fn, useCapture);
+		return true;
+	} else if (elm.attachEvent){
+		var r = elm.attachEvent("on"+evType, fn);
+		return r;
+	} else {
+		alert("Handler could not be removed");
+	}
+}
+function clean_num(str) {
+	str = str.replace(new RegExp(/[^-?0-9.]/g),"");
+	return str;
+}
+function trim(s) {
+	return s.replace(/^\s+|\s+$/g, "");
+}
+function alternate(table) {
+	// Take object table and get all it's tbodies.
+	var tableBodies = table.getElementsByTagName("tbody");
+	// Loop through these tbodies
+	for (var i = 0; i < tableBodies.length; i++) {
+		// Take the tbody, and get all it's rows
+		var tableRows = tableBodies[i].getElementsByTagName("tr");
+		// Loop through these rows
+		// Start at 1 because we want to leave the heading row untouched
+		for (var j = 0; j < tableRows.length; j++) {
+			// Check if j is even, and apply classes for both possible results
+			if ( (j % 2) == 0  ) {
+				if ( !(tableRows[j].className.indexOf('odd') == -1) ) {
+					tableRows[j].className = tableRows[j].className.replace('odd', 'even');
+				} else {
+					if ( tableRows[j].className.indexOf('even') == -1 ) {
+						tableRows[j].className += " even";
+					}
+				}
+			} else {
+				if ( !(tableRows[j].className.indexOf('even') == -1) ) {
+					tableRows[j].className = tableRows[j].className.replace('even', 'odd');
+				} else {
+					if ( tableRows[j].className.indexOf('odd') == -1 ) {
+						tableRows[j].className += " odd";
+					}
+				}
+			} 
+		}
+	}
+}