python-doc-ja-list-open-issues.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

import os
import re
import csv
import urllib
from StringIO import StringIO


def count_hunks(path):
    hunks = 0
    add_lines = 0
    del_lines = 0

    f = open(path)
    in_header = True
    for line in f:
        if in_header:
            if line.startswith("@@"):
                m = re.match(r'@@ -\d+,(\d+) \+\d+,(\d+) @@', line)
                n1, n2 = map(int, m.group(1, 2))
                in_header = False
                hunks += 1
        else:
            if line.startswith(" "):
                n1 -= 1
                n2 -= 1
            elif line.startswith("+"):
                n2 -= 1
                add_lines += 1
            elif line.startswith("-"):
                n1 -= 1
                del_lines += 1
            if n1 == n2 == 0:
                in_header = True
            elif n1 < 0 or n2 < 0:
                raise RuntimeError
    f.close()

    return hunks, add_lines, del_lines


def get_base_path(path):
    return {
        "capi": "c-api/",
        }.get(path.rstrip("/"), path)


def get_diff_path(parent_path, target):
    for path in (os.path.join(parent_path, "diff"), parent_path):
        for ext in (".diff", ".rst.diff"):
            diff = os.path.join(path, target + ext)
            if os.path.exists(diff):
                return diff
    return None


def count_lines(path):
    f = open(path)
    try:
        count = 0
        for line in f:
            count += 1
        return count
    finally:
        f.close()


def main():
    base_url = "http://code.google.com/p/python-doc-ja/issues/csv"
    colspecs = ["ID", "Status", "Milestone", "Owner", "Summary"]

    url = base_url + "?can=2&colspec=%s" % ("%20".join(colspecs))

    f = urllib.urlopen(url)
    content = f.read()
    f.close()

    data = []

    reader = csv.reader(StringIO(content))

    # skip header
    header = reader.next()

    for row in reader:
        if len(row) == 0:
            continue
        id, status, milestone, owner, summary, labels = row

        m = re.match(r'^(.*/)?(.*)の翻訳', summary)
        if m is None:
            print "Ignored: [%s] %s" % (id, summary)
            continue

        path = get_base_path(m.group(1).lower())
        target = m.group(2).strip()
        orig_path = os.path.join(path, target)
        diff = get_diff_path(path, target)
        if diff is None:
            print "Not found diff file: %s in %s" % (target, path)
            if os.path.exists(orig_path):
                lines = count_lines(orig_path)
                data.append((1, lines, 0, orig_path, row))
            continue

        hunks, add_lines, del_lines = count_hunks(diff)
        data.append((hunks, add_lines, del_lines, path + target, row))

    def keyfunc(x):
        return (x[1] + x[2], x[3])
        # return x[3]

    for hunks, add_lines, del_lines, path, row in sorted(data, key=keyfunc):
        id, status, milestone, owner, summary, labels = row
        if status in ("New", "Accepted") and owner == "":
            extra = ""
        else:
            if owner == "":
                owner = "someone"
            extra = " [%s by %s]" % (status, owner)
        print "+%d -%d (%d hunk%s) %s%s" % (
            add_lines, del_lines, hunks, ["s", ""][hunks == 1], path, extra)


if __name__ == '__main__':
    main()