Parse git commit in Python.

git-commit.py

def parse_commit(commit):
    r = {}
    info, diffstat = commit.split("ENDOFOUTPUTGITMESSAGEHERE")
    info = info.strip()
    lines = info.split('\n')
    r["sha1"] = lines[0]
    r["parent"] = lines[1]
    r["author"] = lines[2]
    r["commiter"] = lines[3]
    r["timestamp"] = lines[4]
    r["message"] = '\n'.join(lines[5:])
    r["diffstat"] = diffstat.strip()
    return r

if __name__ == "__main__":
    # git show --numstat --summary --pretty=format:"%H%n%P%n%aN \
    # <%ae>%n%cN <%ce>%n%ct%n%s%n%b%nENDOFOUTPUTGITMESSAGEHERE" a69e6d0
    # Output is per line:
    #   - commit sha1
    #   - parent
    #   - author
    #   - commiter
    #   - timestamp
    #   - message until ENDOFOUTPUTGITMESSAGEHERE
    #   - diffstat is the rest

    commit = """a69e6d06e94d5486675083e17b3b40a4f849b5e7
d2b16baa2b0c10a3f94327e87017e8ea4c01ae4f
Joe Doe <[email protected]>
Joe Doe <[email protected]>
1365604783
Add documentation.
A first documentation draft for the following:
 - git
 - mysql

ENDOFOUTPUTGITMESSAGEHERE
2       0       docs/xxx.rst
 create mode 100644 docs/types/yyy.rst
"""

    import pprint
    pprint.pprint(parse_commit(commit), indent=4)