Skip to content

Commit

Permalink
0110
Browse files Browse the repository at this point in the history
  • Loading branch information
@osfans
osfans committed Jan 10, 2025
1 parent 69da637 commit 27aa65b
Show file tree
Hide file tree
Showing 28 changed files with 10,528 additions and 121 deletions.
10 changes: 5 additions & 5 deletions tools/tables/__init__.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,9 @@

辭典 = ["漢字","說文","康熙","匯纂","漢大"]
辭典數 = len(辭典)
形碼 = ["異體字","字形變體","字形描述","部件檢索","兩分","總筆畫數","部首餘筆","五筆畫","五筆86版","五筆98版","五筆06版","倉頡三代","倉頡五代","倉頡六代","山人碼LTS","分類"]
形碼 = ["異體字","字形變體","字形描述","部件檢索","兩分","總筆畫數","部首餘筆","五筆畫","五筆86","五筆98","五筆06","倉頡三代","倉頡五代","倉頡六代","山人","分類"]

省_set = {'山西', '貴州', '甘肅', '內蒙古', '澳門', '四川', '山東', '臺灣', '雲南', '廣東', '江蘇', '海外', '吉林', '廣西', '香港', '黑龍江', '河南', '河北', '湖南', '上海', '海南', '寧夏', '北京', '遼寧', '新疆', '安徽', '福建', '重慶', '湖北', '浙江', '靑海', '江西', '陝西', '天津', '西藏'}
省集 = {'山西', '貴州', '甘肅', '內蒙古', '澳門', '四川', '山東', '臺灣', '雲南', '廣東', '江蘇', '海外', '吉林', '廣西', '香港', '黑龍江', '河南', '河北', '湖南', '上海', '海南', '寧夏', '北京', '遼寧', '新疆', '安徽', '福建', '重慶', '湖北', '浙江', '靑海', '江西', '陝西', '天津', '西藏'}

n2o_dict = {}
o2n_dict = {}
Expand Down Expand Up @@ -171,7 +171,7 @@ def 獲取同音字頻(get=False):
調典[調值] = 調
語.調典 = 調典
語.info = d
語.加載()
語.讀()
if 語.音節數 > 0:
for 字組 in 語.聲韻典.values():
if len(字組) < 2: continue
Expand Down Expand Up @@ -270,7 +270,7 @@ def getLangs(dicts, 參數, args):
for 字乙 in 字組乙:
字頻 += 同音字頻["".join(sorted((字甲, 字乙)))]
if 字頻 < 1.8 * n:
語.誤.append(f"{字甲}可能不讀[{音}]{''.join(字組乙)[:4]}")
語.誤.append(f"【{字甲}】可能不讀[{音}]{''.join(字組乙)[:4]}")
語.info["解析日志"] = None
語.info["同音字表"] = None
if 語.誤:
Expand Down Expand Up @@ -326,7 +326,7 @@ def getLangs(dicts, 參數, args):
if 項 not in 字.info: 字.info[項] = None
字.info["字數"] = len(dicts)
字.info["說明"] = "語言數：%d\n\n%s"%(數, 字.說明)
省表 = sorted(省_set, key=普拼)
省表 = sorted(省集, key=普拼)
if "海外" in 省表:
省表.remove("海外")
省表.append("海外")
Expand Down
4 changes: 3 additions & 1 deletion tools/tables/_縣志.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ def 行轉調類(自, 行, 格式=r"\[(\d+)\]"):

def 統(自, 行):
行 = _表.統(自, 行)
名 = 自.名
名 = 自.簡稱
if 名 in ("永州嵐角山", "賀州南鄕", "松江天馬", "運城", "興縣","豐城","豐城鐵路","新建","賀州江坪"):
行 = 行.lstrip("ø")
elif 名 in ("江夏湖泗"):
Expand Down Expand Up @@ -141,6 +141,8 @@ def 統(自, 行):
行 = 行.replace("/", "")
elif 名 in ("海門"):
if 行.startswith("#"): return "#"
elif 名 in ("長治"):
if 行.startswith("#"): return "#"
elif 名 in ("博白","東莞塘角"):
if 行.startswith("#"): return "#"
果 = re.findall(r"\[(.*?)(\d+)\]", 行)
Expand Down
24 changes: 12 additions & 12 deletions tools/tables/_表.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -117,7 +117,12 @@ def run2text(run):
if tag:
text = "".join([i + tag for i in text])
if run.font.subscript or (run.font.size and run.font.size < 115000):
text = f"{{{text}}}"
if text.startswith("{") and text.endswith("}"):
pass
elif text.startswith("[") and text.endswith("]"):
pass
else:
text = f"{{{text}}}"
return text

def isDocx(fname):
Expand Down Expand Up @@ -183,10 +188,6 @@ def setmod(自, mod):
def __str__(自):
if 自.__mod: return 自.__mod
return 自.__module__.split(".")[-1]

@property
def 名(自):
return str(自)

def find(自, name):
if os.sep not in name and (isXls(name) or isDocx(name)):
Expand All @@ -208,7 +209,7 @@ def spath(自):
自.文件名 = 自._files[0]
sname = 自.文件名
if not 自.簡稱: 自.簡稱 = 自.info["簡稱"]
if not 自.簡稱: 自.簡稱 = 自.名
if not 自.簡稱: 自.簡稱 = str(自)
if not sname: sname = f"{自.簡稱}.tsv"
g = 自.find(sname)
if not g or len(g) != 1:
Expand Down Expand Up @@ -281,7 +282,7 @@ def _正音(自, 音):
if 自.爲語() and 自.爲音:
音 = 音.strip()
音 = 音.replace("Ǿ", "Ǿ").replace("Ǿ", "").lstrip("∅︀∅Ø〇0").replace("零", "")
if 自.名 != "盛唐": 音 = 音.lstrip("q")
if 自.簡稱 != "盛唐": 音 = 音.lstrip("q")
if 音.startswith("I") or 音.startswith("1"): 音 = "l" + 音[1:]
音 = 音.lower().replace("g", "ɡ").replace("ʼ", "ʰ").replace("'", "ʰ").replace("‘", "ʰ")
if not 音.startswith("h") and "h" in 音:
Expand Down Expand Up @@ -399,10 +400,10 @@ def 聲韻數(自):

def 讀(自, 更新=False):
自.音表.clear()
if 自.過時() or 更新 and 自.spath: 自.更新()
自.音典.clear()
自.聲韻典.clear()
自.d.clear()
if 自.過時() or 更新 and 自.spath: 自.更新()
if not 自.tpath or not os.path.exists(自.tpath): return
for 行 in open(自.tpath,encoding="U8"):
行 = 行.strip()
Expand Down Expand Up @@ -436,7 +437,7 @@ def 讀(自, 更新=False):
py += "{%s}" % 註
else:
if 自.字書:
sep = "▲" if 自.名 == "匯纂" else "\t"
sep = "▲" if 自.簡稱 == "匯纂" else "\t"
py2, 註 = py.split(sep, 1)
py = ("\n\n" if 自.d[字] else "") + py2 + sep + 自.分註(註)
elif 自.簡稱 in ("部件檢索","字形描述"):
Expand All @@ -445,14 +446,13 @@ def 讀(自, 更新=False):
if py not in 自.d[字]:
自.d[字].append(py)

def 加載(自, dicts=None, 更新=False):
def 加載(自, dicts, 更新=False):
自.讀(更新)
if not 自.d: return
if dicts is None: return
for 字, 音集 in 自.d.items():
if 字 not in dicts:
dicts[字] = {"漢字": 字}
dicts[字][自.名] = "\t".join(音集)
dicts[字][自.簡稱] = "\t".join(音集)

def 析(自, 列):
return tuple(列[:3])
Expand Down
2 changes: 1 addition & 1 deletion tools/tables/_跳跳老鼠.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ class 表(_表):
聲韻 = ""

def 析(自, 列):
名 = 自.名
名 = 自.簡稱
音 = ""
調 = ""
if 名 in ("臨川","奉新宋埠"):
Expand Down
2 changes: 1 addition & 1 deletion tools/tables/_音典.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
class 表(_表):

def 析(自, 列):
名 = 自.名
名 = 自.簡稱
字 = ""
音 = ""
音標 = ""
Expand Down
Loading

0 comments on commit 27aa65b

Please sign in to comment.