CJK kinsoku line breaking: hanging punctuation set · case 01

"""Failure Map reference implementation. Python standard library only."""
import json

N = 1
observations = []
def solve(x):
    text, L = x
    NO_START = '、。，．）」』！？ーぁぃぅぇぉっゃゅょ'
    NO_END = '（「『'
    HANG = '、。，．'
    lines = []
    pos = 0
    n = len(text)
    while pos < n:
        end = pos + L
        if end >= n:
            lines.append(text[pos:])
            break
        if text[end] in NO_START and (end + 1 >= n or text[end + 1] not in NO_START):
            end += 1
        else:
            while end > pos + 1 and text[end] in NO_START:
                end -= 1
            while end > pos + 1 and text[end - 1] in NO_END:
                end -= 1
        lines.append(text[pos:end])
        pos = end
    return lines
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
fixtures = [[('closing bracket pushes out', ['日本語文」字組版', 4], ['日本語', '文」字組', '版']), ('regression: hanging punctuation set', ['（ーう「語っい」えあえ', 7], ['（ーう「語っ', 'い」えあえ']), ('regression: hanging punctuation set', ['い本いおお（）こーお』」きくこおきか', 3], ['い本い', 'おお', '（）', 'こー', 'お』」', 'きくこ', 'おきか']), ('regression: hanging punctuation set', ['、あゃく文え、『か、）版」日ゃ（文『か', 3], ['、あゃ', 'く文え、', '『', 'か、）', '版」', '日ゃ', '（文', '『か']), ('period hangs past the measure', ['日本語文。字組版', 4], ['日本語文。', '字組版']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('control layout', ['文字くい「「いおい字こく字っーー、かお本', 6], ['文字くい', '「「いおい字', 'こく字っーー、', 'かお本']), ('control layout', ['』おゃ本版「文おゃ「」。語き', 7], ['』おゃ本版「文', 'おゃ「」。語き'])], [('regression: hanging punctuation set', ['版うゃかくかうけー', 4], ['版うゃか', 'くかう', 'けー']), ('regression: hanging punctuation set', ['文か）うこ「け組ゃ版ゃ字ゃい、本え版', 5], ['文か）うこ', '「け組ゃ', '版ゃ字ゃい、', '本え版']), ('regression: hanging punctuation set', ['文け『い、あ。「日っ」『', 3], ['文け', '『い、', 'あ。', '「', '日っ」', '『']), ('regression: hanging punctuation set', ['「『ゃうくゃ組え（日本う」」」語（ー', 3], ['「『ゃ', 'うくゃ', '組え', '（日本', 'う', '」」」', '語（ー']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('small kana prohibited at line start', ['日本語かっこいい', 4], ['日本語', 'かっこい', 'い']), ('control layout', ['かいあ』え」き』', 8], ['かいあ』え」き』']), ('control layout', ['」う』（文え））ー文、本うく語」え、ー』（』っ', 5], ['」う』（文', 'え））ー文、', '本うく語」', 'え、ー』', '（』っ'])], [('regression: hanging punctuation set', ['「うえ『いーあ』『ー日）字日こく', 5], ['「うえ', '『いーあ』', '『ー日）字', '日こく']), ('regression: hanging punctuation set', ['かかー語ういいえ『。組おくこ、く」', 4], ['かかー語', 'ういいえ', '『。組お', 'くこ、', 'く」']), ('regression: hanging punctuation set', ['ゃ（版）文う字あゃ本語『組」', 3], ['ゃ', '（版）', '文う字', 'あゃ本', '語', '『組」']), ('regression: hanging punctuation set', ['く』』えき字『（っおゃく」く版えあ版文、', 6], ['く』』えき字', '『（っおゃ', 'く」く版えあ', '版文、']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('opening bracket at line end', ['日本語「文字」組版', 4], ['日本語', '「文字」', '組版']), ('control layout', ['文語日（語く文あ', 4], ['文語日', '（語く文', 'あ']), ('control layout', ['（い）」『ーえけかえ字っーき組っ', 7], ['（い）」『ーえ', 'けかえ字っーき', '組っ'])], [('regression: hanging punctuation set', ['「版お語あ「）版」『字いか日本', 6], ['「版お語あ', '「）版」『字', 'いか日本']), ('regression: hanging punctuation set', ['きき組え』うおっ（い', 7], ['きき組え』う', 'おっ（い']), ('regression: hanging punctuation set', ['く文『けいえ「日）語）文』、こっ（か文お「）」', 4], ['く文『け', 'いえ', '「日）', '語）文』、', 'こっ（か', '文お', '「）」']), ('regression: hanging punctuation set', ['ゃ「、お。おっけ）い本文きっ』え版日』）本', 8], ['ゃ「、お。おっ', 'け）い本文きっ』', 'え版日』）本']), ('closing bracket pushes out', ['日本語文」字組版', 4], ['日本語', '文」字組', '版']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('control layout', ['か）ーお組こ『組文ーっ版っっ文。', 3], ['か）ー', 'お組こ', '『組', '文ーっ', '版っっ', '文。']), ('control layout', ['。き日く。文。き。', 8], ['。き日く。文。き。'])], [('regression: hanging punctuation set', ['え本『」お、版あ、くあゃお、かきこ語日」おい（語', 5], ['え本『」お、', '版あ、く', 'あゃお、か', 'きこ語日」', 'おい（語']), ('regression: hanging punctuation set', ['』（『組け字』、き『あ）っ組』か語ゃ', 3], ['』', '（『組', 'け字』、', 'き', '『', 'あ）っ', '組』か', '語ゃ']), ('regression: hanging punctuation set', ['お」本版「きうい）おかきえ字）', 5], ['お」本版', '「きうい）', 'おかきえ', '字）']), ('regression: hanging punctuation set', ['」日あっ日っ）うゃ文（版けうーくこ）「', 6], ['」日あっ', '日っ）うゃ文', '（版けうーく', 'こ）「']), ('closing bracket pushes out', ['日本語文」字組版', 4], ['日本語', '文」字組', '版']), ('small kana prohibited at line start', ['日本語かっこいい', 4], ['日本語', 'かっこい', 'い']), ('control layout', ['き字こ版、）語版い字ゃいお字こ字ゃ', 3], ['き字こ', '版、）', '語版い', '字ゃい', 'お字こ', '字ゃ']), ('control layout', ['え、かけ語か「『いい日う字え', 6], ['え、かけ語か', '「『いい日う', '字え'])]]
for label, args, expected in fixtures[N - 1]:
    check(label, solve(args), expected)
print(json.dumps({"observations": observations, "passed": all(x["passed"] for x in observations)}, ensure_ascii=False))
raise SystemExit(0 if all(x["passed"] for x in observations) else 1)

SHA-256 / 196a46fcfa74c3ff730304f9fd78b13d38076ae51ce6abdd7938fa5c1e35c66b

"""Failure Map reference implementation. Python standard library only."""
import json

N = 1
observations = []
def solve(x):
    text, L = x
    NO_START = '、。，．）」』！？ーぁぃぅぇぉっゃゅょ'
    NO_END = '（「『'
    HANG = '、。，．'
    lines = []
    pos = 0
    n = len(text)
    while pos < n:
        end = pos + L
        if end >= n:
            lines.append(text[pos:])
            break
        if text[end] in HANG + '）」' and (end + 1 >= n or text[end + 1] not in NO_START):
            end += 1
        else:
            while end > pos + 1 and text[end] in NO_START:
                end -= 1
            while end > pos + 1 and text[end - 1] in NO_END:
                end -= 1
        lines.append(text[pos:end])
        pos = end
    return lines
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
fixtures = [[('closing bracket pushes out', ['日本語文」字組版', 4], ['日本語', '文」字組', '版']), ('regression: hanging punctuation set', ['（ーう「語っい」えあえ', 7], ['（ーう「語っ', 'い」えあえ']), ('regression: hanging punctuation set', ['い本いおお（）こーお』」きくこおきか', 3], ['い本い', 'おお', '（）', 'こー', 'お』」', 'きくこ', 'おきか']), ('regression: hanging punctuation set', ['、あゃく文え、『か、）版」日ゃ（文『か', 3], ['、あゃ', 'く文え、', '『', 'か、）', '版」', '日ゃ', '（文', '『か']), ('period hangs past the measure', ['日本語文。字組版', 4], ['日本語文。', '字組版']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('control layout', ['文字くい「「いおい字こく字っーー、かお本', 6], ['文字くい', '「「いおい字', 'こく字っーー、', 'かお本']), ('control layout', ['』おゃ本版「文おゃ「」。語き', 7], ['』おゃ本版「文', 'おゃ「」。語き'])], [('regression: hanging punctuation set', ['版うゃかくかうけー', 4], ['版うゃか', 'くかう', 'けー']), ('regression: hanging punctuation set', ['文か）うこ「け組ゃ版ゃ字ゃい、本え版', 5], ['文か）うこ', '「け組ゃ', '版ゃ字ゃい、', '本え版']), ('regression: hanging punctuation set', ['文け『い、あ。「日っ」『', 3], ['文け', '『い、', 'あ。', '「', '日っ」', '『']), ('regression: hanging punctuation set', ['「『ゃうくゃ組え（日本う」」」語（ー', 3], ['「『ゃ', 'うくゃ', '組え', '（日本', 'う', '」」」', '語（ー']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('small kana prohibited at line start', ['日本語かっこいい', 4], ['日本語', 'かっこい', 'い']), ('control layout', ['かいあ』え」き』', 8], ['かいあ』え」き』']), ('control layout', ['」う』（文え））ー文、本うく語」え、ー』（』っ', 5], ['」う』（文', 'え））ー文、', '本うく語」', 'え、ー』', '（』っ'])], [('regression: hanging punctuation set', ['「うえ『いーあ』『ー日）字日こく', 5], ['「うえ', '『いーあ』', '『ー日）字', '日こく']), ('regression: hanging punctuation set', ['かかー語ういいえ『。組おくこ、く」', 4], ['かかー語', 'ういいえ', '『。組お', 'くこ、', 'く」']), ('regression: hanging punctuation set', ['ゃ（版）文う字あゃ本語『組」', 3], ['ゃ', '（版）', '文う字', 'あゃ本', '語', '『組」']), ('regression: hanging punctuation set', ['く』』えき字『（っおゃく」く版えあ版文、', 6], ['く』』えき字', '『（っおゃ', 'く」く版えあ', '版文、']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('opening bracket at line end', ['日本語「文字」組版', 4], ['日本語', '「文字」', '組版']), ('control layout', ['文語日（語く文あ', 4], ['文語日', '（語く文', 'あ']), ('control layout', ['（い）」『ーえけかえ字っーき組っ', 7], ['（い）」『ーえ', 'けかえ字っーき', '組っ'])], [('regression: hanging punctuation set', ['「版お語あ「）版」『字いか日本', 6], ['「版お語あ', '「）版」『字', 'いか日本']), ('regression: hanging punctuation set', ['きき組え』うおっ（い', 7], ['きき組え』う', 'おっ（い']), ('regression: hanging punctuation set', ['く文『けいえ「日）語）文』、こっ（か文お「）」', 4], ['く文『け', 'いえ', '「日）', '語）文』、', 'こっ（か', '文お', '「）」']), ('regression: hanging punctuation set', ['ゃ「、お。おっけ）い本文きっ』え版日』）本', 8], ['ゃ「、お。おっ', 'け）い本文きっ』', 'え版日』）本']), ('closing bracket pushes out', ['日本語文」字組版', 4], ['日本語', '文」字組', '版']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('control layout', ['か）ーお組こ『組文ーっ版っっ文。', 3], ['か）ー', 'お組こ', '『組', '文ーっ', '版っっ', '文。']), ('control layout', ['。き日く。文。き。', 8], ['。き日く。文。き。'])], [('regression: hanging punctuation set', ['え本『」お、版あ、くあゃお、かきこ語日」おい（語', 5], ['え本『」お、', '版あ、く', 'あゃお、か', 'きこ語日」', 'おい（語']), ('regression: hanging punctuation set', ['』（『組け字』、き『あ）っ組』か語ゃ', 3], ['』', '（『組', 'け字』、', 'き', '『', 'あ）っ', '組』か', '語ゃ']), ('regression: hanging punctuation set', ['お」本版「きうい）おかきえ字）', 5], ['お」本版', '「きうい）', 'おかきえ', '字）']), ('regression: hanging punctuation set', ['」日あっ日っ）うゃ文（版けうーくこ）「', 6], ['」日あっ', '日っ）うゃ文', '（版けうーく', 'こ）「']), ('closing bracket pushes out', ['日本語文」字組版', 4], ['日本語', '文」字組', '版']), ('small kana prohibited at line start', ['日本語かっこいい', 4], ['日本語', 'かっこい', 'い']), ('control layout', ['き字こ版、）語版い字ゃいお字こ字ゃ', 3], ['き字こ', '版、）', '語版い', '字ゃい', 'お字こ', '字ゃ']), ('control layout', ['え、かけ語か「『いい日う字え', 6], ['え、かけ語か', '「『いい日う', '字え'])]]
for label, args, expected in fixtures[N - 1]:
    check(label, solve(args), expected)
print(json.dumps({"observations": observations, "passed": all(x["passed"] for x in observations)}, ensure_ascii=False))
raise SystemExit(0 if all(x["passed"] for x in observations) else 1)

SHA-256 / a11b9b4a528b1bbab64410217315fbcf97a60494f57fef446ef3b97e6816b235

"""Failure Map reference implementation. Python standard library only."""
import json

N = 1
observations = []
def solve(x):
    text, L = x
    NO_START = '、。，．）」』！？ーぁぃぅぇぉっゃゅょ'
    NO_END = '（「『'
    HANG = '、。，．'
    lines = []
    pos = 0
    n = len(text)
    while pos < n:
        end = pos + L
        if end >= n:
            lines.append(text[pos:])
            break
        if text[end] in HANG and (end + 1 >= n or text[end + 1] not in NO_START):
            end += 1
        else:
            while end > pos + 1 and text[end] in NO_START:
                end -= 1
            while end > pos + 1 and text[end - 1] in NO_END:
                end -= 1
        lines.append(text[pos:end])
        pos = end
    return lines
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
fixtures = [[('closing bracket pushes out', ['日本語文」字組版', 4], ['日本語', '文」字組', '版']), ('regression: hanging punctuation set', ['（ーう「語っい」えあえ', 7], ['（ーう「語っ', 'い」えあえ']), ('regression: hanging punctuation set', ['い本いおお（）こーお』」きくこおきか', 3], ['い本い', 'おお', '（）', 'こー', 'お』」', 'きくこ', 'おきか']), ('regression: hanging punctuation set', ['、あゃく文え、『か、）版」日ゃ（文『か', 3], ['、あゃ', 'く文え、', '『', 'か、）', '版」', '日ゃ', '（文', '『か']), ('period hangs past the measure', ['日本語文。字組版', 4], ['日本語文。', '字組版']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('control layout', ['文字くい「「いおい字こく字っーー、かお本', 6], ['文字くい', '「「いおい字', 'こく字っーー、', 'かお本']), ('control layout', ['』おゃ本版「文おゃ「」。語き', 7], ['』おゃ本版「文', 'おゃ「」。語き'])], [('regression: hanging punctuation set', ['版うゃかくかうけー', 4], ['版うゃか', 'くかう', 'けー']), ('regression: hanging punctuation set', ['文か）うこ「け組ゃ版ゃ字ゃい、本え版', 5], ['文か）うこ', '「け組ゃ', '版ゃ字ゃい、', '本え版']), ('regression: hanging punctuation set', ['文け『い、あ。「日っ」『', 3], ['文け', '『い、', 'あ。', '「', '日っ」', '『']), ('regression: hanging punctuation set', ['「『ゃうくゃ組え（日本う」」」語（ー', 3], ['「『ゃ', 'うくゃ', '組え', '（日本', 'う', '」」」', '語（ー']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('small kana prohibited at line start', ['日本語かっこいい', 4], ['日本語', 'かっこい', 'い']), ('control layout', ['かいあ』え」き』', 8], ['かいあ』え」き』']), ('control layout', ['」う』（文え））ー文、本うく語」え、ー』（』っ', 5], ['」う』（文', 'え））ー文、', '本うく語」', 'え、ー』', '（』っ'])], [('regression: hanging punctuation set', ['「うえ『いーあ』『ー日）字日こく', 5], ['「うえ', '『いーあ』', '『ー日）字', '日こく']), ('regression: hanging punctuation set', ['かかー語ういいえ『。組おくこ、く」', 4], ['かかー語', 'ういいえ', '『。組お', 'くこ、', 'く」']), ('regression: hanging punctuation set', ['ゃ（版）文う字あゃ本語『組」', 3], ['ゃ', '（版）', '文う字', 'あゃ本', '語', '『組」']), ('regression: hanging punctuation set', ['く』』えき字『（っおゃく」く版えあ版文、', 6], ['く』』えき字', '『（っおゃ', 'く」く版えあ', '版文、']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('opening bracket at line end', ['日本語「文字」組版', 4], ['日本語', '「文字」', '組版']), ('control layout', ['文語日（語く文あ', 4], ['文語日', '（語く文', 'あ']), ('control layout', ['（い）」『ーえけかえ字っーき組っ', 7], ['（い）」『ーえ', 'けかえ字っーき', '組っ'])], [('regression: hanging punctuation set', ['「版お語あ「）版」『字いか日本', 6], ['「版お語あ', '「）版」『字', 'いか日本']), ('regression: hanging punctuation set', ['きき組え』うおっ（い', 7], ['きき組え』う', 'おっ（い']), ('regression: hanging punctuation set', ['く文『けいえ「日）語）文』、こっ（か文お「）」', 4], ['く文『け', 'いえ', '「日）', '語）文』、', 'こっ（か', '文お', '「）」']), ('regression: hanging punctuation set', ['ゃ「、お。おっけ）い本文きっ』え版日』）本', 8], ['ゃ「、お。おっ', 'け）い本文きっ』', 'え版日』）本']), ('closing bracket pushes out', ['日本語文」字組版', 4], ['日本語', '文」字組', '版']), ('period followed by bracket cannot hang', ['日本語文。」字組', 4], ['日本語', '文。」字', '組']), ('control layout', ['か）ーお組こ『組文ーっ版っっ文。', 3], ['か）ー', 'お組こ', '『組', '文ーっ', '版っっ', '文。']), ('control layout', ['。き日く。文。き。', 8], ['。き日く。文。き。'])], [('regression: hanging punctuation set', ['え本『」お、版あ、くあゃお、かきこ語日」おい（語', 5], ['え本『」お、', '版あ、く', 'あゃお、か', 'きこ語日」', 'おい（語']), ('regression: hanging punctuation set', ['』（『組け字』、き『あ）っ組』か語ゃ', 3], ['』', '（『組', 'け字』、', 'き', '『', 'あ）っ', '組』か', '語ゃ']), ('regression: hanging punctuation set', ['お」本版「きうい）おかきえ字）', 5], ['お」本版', '「きうい）', 'おかきえ', '字）']), ('regression: hanging punctuation set', ['」日あっ日っ）うゃ文（版けうーくこ）「', 6], ['」日あっ', '日っ）うゃ文', '（版けうーく', 'こ）「']), ('closing bracket pushes out', ['日本語文」字組版', 4], ['日本語', '文」字組', '版']), ('small kana prohibited at line start', ['日本語かっこいい', 4], ['日本語', 'かっこい', 'い']), ('control layout', ['き字こ版、）語版い字ゃいお字こ字ゃ', 3], ['き字こ', '版、）', '語版い', '字ゃい', 'お字こ', '字ゃ']), ('control layout', ['え、かけ語か「『いい日う字え', 6], ['え、かけ語か', '「『いい日う', '字え'])]]
for label, args, expected in fixtures[N - 1]:
    check(label, solve(args), expected)
print(json.dumps({"observations": observations, "passed": all(x["passed"] for x in observations)}, ensure_ascii=False))
raise SystemExit(0 if all(x["passed"] for x in observations) else 1)

SHA-256 / 840136330e48d3376c9295ffbfe51f389d83f2ecada3c08f6bcd44eb2ac3a8b1