jesse-uxandJesse_Chen
b8eef75871
完整数据版第二轮。年运章写出资料包里已有的节，没有数据的不新算。大运解释补回可能段落。瑜伽作用不再断言寿命。术语替换不进标识符。罗睺和计都不写守护第未列出宫。未合入 staging。
912 lines
47 KiB
Python
912 lines
47 KiB
Python
#!/usr/bin/env python3
|
||
"""PL9 report language normalization and leakage gates.
|
||
|
||
The term policy is based on this repository's StarTrack language-bridge
|
||
boundary and the Jyotish wording guidance in references/modern-language-guide.md.
|
||
It only changes reader-facing labels; it does not alter calculation payloads.
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import re
|
||
from typing import Any
|
||
|
||
|
||
def replace_natural_language_term(text: str, raw: str, public: str) -> str:
|
||
"""Replace one glossary term in prose only.
|
||
|
||
Identifiers and backtick spans stay as written. A trailing English plural
|
||
``s`` is consumed with the English word, so it is not left after Chinese.
|
||
"""
|
||
|
||
if not text or not raw:
|
||
return text
|
||
plural = "s?" if re.search(r"[A-Za-z]$", raw) and not raw.endswith("s") else ""
|
||
pattern = re.compile(rf"(?<![A-Za-z0-9_]){re.escape(raw)}{plural}(?![A-Za-z0-9_])")
|
||
parts = re.split(r"(`[^`]*`)", text)
|
||
return "".join(
|
||
part if index % 2 else pattern.sub(public, part)
|
||
for index, part in enumerate(parts)
|
||
)
|
||
|
||
|
||
_LIFESPAN_ASSERTION = re.compile(
|
||
r"长寿|寿命长|短寿|寿命|longevity|lifespan|long life|short life",
|
||
re.IGNORECASE,
|
||
)
|
||
_LIFESPAN_EFFECT_ZH = "传统上与体质和恢复力有关，仅作参考"
|
||
_LIFESPAN_EFFECT_EN = "Traditionally associated with constitution and recovery. Reference only."
|
||
|
||
|
||
def strip_han_plural_s(text: str) -> str:
|
||
"""Remove a Latin plural s left on Chinese after a glossary replace."""
|
||
|
||
return re.sub(r"([一-鿿])s\b", r"\1", text)
|
||
|
||
|
||
def soften_lifespan_wording(text: str, language: str = "zh") -> str:
|
||
"""Drop lifespan assertions from an effect cell. Yoga names are not passed here."""
|
||
|
||
if not text or not _LIFESPAN_ASSERTION.search(str(text)):
|
||
return text
|
||
if language == "en":
|
||
return _LIFESPAN_EFFECT_EN
|
||
return _LIFESPAN_EFFECT_ZH
|
||
|
||
|
||
ZH_TERM_REPLACEMENTS: tuple[tuple[str, str], ...] = (
|
||
("Natural friends", "天然友星"),
|
||
("Natural enemies", "天然敌星"),
|
||
("Temporary relation", "临时关系"),
|
||
("Planet 1", "行星1"),
|
||
("Planet 2", "行星2"),
|
||
("Planet", "行星"),
|
||
("planet", "行星"),
|
||
("sign", "星座"),
|
||
("longitude", "黄经"),
|
||
("field", "字段"),
|
||
("value", "数值"),
|
||
("title", "标题"),
|
||
("target", "目标"),
|
||
("anchor", "依据"),
|
||
("yoga", "瑜伽"),
|
||
("dt_ut", "UTC 时间"),
|
||
("dt_local", "本地时间"),
|
||
("sun_lon", "太阳黄经"),
|
||
("year_lord", "年主星"),
|
||
("field_status", "字段状态"),
|
||
("muntha_house", "Muntha 宫位"),
|
||
("muntha_sign", "Muntha 星座"),
|
||
("muntha_lord", "Muntha 主星"),
|
||
("munthesh", "Muntha 宫主"),
|
||
("Nakshatra Scheme", "星宿身体对应表"),
|
||
("Opinion 1", "说法一"),
|
||
("Opinion 2", "说法二"),
|
||
("Graha Avastha", "Graha Avastha（行星状态）"),
|
||
("Jagradadi", "醒睡状态"),
|
||
("Baladi", "年龄状态"),
|
||
("Lajjitadi", "羞惭等状态"),
|
||
("Deeptadi", "明亮等状态"),
|
||
("Shyanadi", "卧姿等状态"),
|
||
("Shayanadi", "卧姿等状态"),
|
||
("Degree", "落座度数"),
|
||
("Declination", "赤纬"),
|
||
("Speed", "速度"),
|
||
("House", "宫位"),
|
||
("Sign", "星座"),
|
||
("Lord", "宫主"),
|
||
("Score", "分数"),
|
||
("Bala", "年龄状态"),
|
||
("Jagrat", "醒睡状态"),
|
||
("Aspect", "相位"),
|
||
("Exact degree", "精确角度"),
|
||
("Actual difference", "实际角距"),
|
||
("Orb", "容许度"),
|
||
("Applying", "入相"),
|
||
("From house", "起始宫位"),
|
||
("Target house", "目标宫位"),
|
||
("Aspect type", "相位类型"),
|
||
("Special", "特殊相位"),
|
||
("Category", "类别"),
|
||
("Strength", "强度"),
|
||
("Combination", "组合条件"),
|
||
("Effects / notes", "作用说明"),
|
||
("friends:", "友星："),
|
||
("enemies:", "敌星："),
|
||
("True", "是"),
|
||
("False", "否"),
|
||
("conjunction", "合相"),
|
||
("opposition", "对冲"),
|
||
("special", "特殊组合"),
|
||
("solar_yoga", "太阳瑜伽"),
|
||
("lunar_yoga", "月亮瑜伽"),
|
||
("kalatra", "婚恋"),
|
||
("durbhaga", "不利组合"),
|
||
("moderate", "中等"),
|
||
("common", "常见"),
|
||
("strong", "强"),
|
||
("weak", "弱"),
|
||
("not separately listed", "未单独列出"),
|
||
("ownership", "守护宫"),
|
||
("dignity", "尊贵状态"),
|
||
("house placement", "落宫"),
|
||
("natural significations", "自然象征"),
|
||
("functional role", "功能角色"),
|
||
("Graha Avasthas - Planets and their Moods", "Graha Avastha（行星状态与情绪）"),
|
||
("Mangala / Sade Sati / Dosha Results", "火星婚姻煞 / Sade Sati / Dosha 结果"),
|
||
("Mangal / Kuja Dosha", "火星婚姻煞（Mangala/Kuja Dosha）"),
|
||
("Poorvashadha", "前阿沙陀"),
|
||
("Poorva Ashadha", "前阿沙陀"),
|
||
("Uttara Phalg.", "后破伽"),
|
||
("Uttara Phalguni", "后破伽"),
|
||
("Uttarashadha", "后阿沙陀"),
|
||
("Uttara Ashadha", "后阿沙陀"),
|
||
("Uttarabhadra", "后跋陀罗"),
|
||
("Uttara Bhadrapada", "后跋陀罗"),
|
||
("Moola", "Mula（根、本源）"),
|
||
("Mula", "Mula（根、本源）"),
|
||
("Both thighs", "双侧大腿"),
|
||
("Both feet", "双脚"),
|
||
("Private parts", "私密部位"),
|
||
("Sides of body", "身体两侧"),
|
||
("Back", "背部"),
|
||
("Left side", "左侧"),
|
||
("Left hand", "左手"),
|
||
("Waist", "腰部"),
|
||
("Waiste", "腰部"),
|
||
("Shins", "小腿胫部"),
|
||
("Swapna", "梦眠"),
|
||
("Dreamful", "多梦"),
|
||
("Mrita", "死寂"),
|
||
("State of death", "死寂状态"),
|
||
("Sushupti", "熟睡"),
|
||
("State of sleep", "睡眠状态"),
|
||
("Jagrad", "觉醒"),
|
||
("Wakefulness", "清醒"),
|
||
("Kumaravastha", "少年期"),
|
||
("Adolescence", "青春期"),
|
||
("Balavastha", "童年期"),
|
||
("Childhood", "童年"),
|
||
("Vriddha", "老年期"),
|
||
("Old age", "老年"),
|
||
("Mudit Kshobit", "喜悦中带扰动"),
|
||
("Trushit Mudit", "渴求中带喜悦"),
|
||
("Kshudit Trushit", "饥渴不安"),
|
||
("Mudit", "喜悦"),
|
||
("Khala", "粗劣"),
|
||
("Mudita", "愉悦"),
|
||
("Delighted", "愉悦"),
|
||
("Shanta", "平静"),
|
||
("Quiescent", "安静"),
|
||
("Deena", "匮乏"),
|
||
("Deficient", "不足"),
|
||
("Swastha", "稳定"),
|
||
("Stable", "稳定"),
|
||
("Nidra", "睡眠"),
|
||
("Sleep", "睡眠"),
|
||
("Gamenecchha", "欲行"),
|
||
("Eager to go", "急于行动"),
|
||
("Shayana", "卧躺"),
|
||
("Recumbent", "卧躺"),
|
||
("Sabhayam Vasti", "集会中"),
|
||
("in an assembly", "在集会中"),
|
||
("Infant", "婴幼期"),
|
||
("Young", "青年期"),
|
||
("Youth", "壮年期"),
|
||
("Dead", "死寂"),
|
||
("Awake", "觉醒"),
|
||
("Dreaming", "梦眠"),
|
||
("Trushita", "渴求"),
|
||
("Kshobhita", "扰动"),
|
||
("Vikala", "失衡"),
|
||
("Kautuka", "好奇"),
|
||
("Agama", "学习/趋近"),
|
||
("Panapara", "续宫"),
|
||
("Apoklima", "果宫"),
|
||
("Kendra", "角宫"),
|
||
("Benefic", "自然吉星"),
|
||
("Malefic", "自然凶星"),
|
||
)
|
||
|
||
|
||
ZH_ALLOWED_LATIN_TOKENS = {
|
||
"AI", "AD", "PD", "MD", "PL9", "KP", "BPHS", "PVR", "D1", "D2", "D3", "D4",
|
||
"D5", "D6", "D7", "D8", "D9", "D10", "D11", "D12", "D16", "D20", "D24",
|
||
"D27", "D30", "D40", "D45", "D60", "Rashi", "Navamsha", "Bhava", "Sripati",
|
||
"Sudarshan", "Sudarshana", "Upagraha", "Lagna", "Arudha", "Upapada", "Pada",
|
||
"Dasha", "Vimshottari", "Ashtottari", "Yogini", "Kala", "Chakra", "Jaimini",
|
||
"Narayana", "Sthira", "Drig", "Shoola", "Tribhagi", "Sade", "Sati", "Dhayya",
|
||
"Kantaka", "Varshaphala", "Tajika", "Mudda", "Patyayini", "Saham", "Sahams",
|
||
"Shadbala", "Ashtakavarga", "BAV", "SAV", "Pinda", "Avastha", "Vimsopaka",
|
||
"Paravatamsa", "Simhasanamsa", "Rahu", "Ketu", "Sun", "Moon", "Mars",
|
||
"Mercury", "Jupiter", "Venus", "Saturn", "Ashwini", "Bharani", "Krittika",
|
||
"Virupa", "Sthana", "Dig", "Drik", "Chesta",
|
||
"Rohini", "Mrigashira", "Ardra", "Punarvasu", "Pushya", "Ashlesha", "Magha",
|
||
"Purva", "Uttara", "Phalguni", "Hasta", "Chitra", "Swati", "Vishakha",
|
||
"Anuradha", "Jyeshtha", "Mula", "Ashadha", "Shravana", "Dhanishta",
|
||
"Shatabhisha", "Bhadrapada", "Revati",
|
||
"benefic", "malefic", "debilitated", "Neecha", "Bhanga", "and",
|
||
"functional_benefic", "functional_malefic", "functional_neutral",
|
||
"natural_benefic", "natural_malefic", "natural_role_not_returned",
|
||
"functional_role_not_returned",
|
||
}
|
||
|
||
|
||
ZH_FORBIDDEN_MIXED_PHRASES = (
|
||
"General effects during",
|
||
"General effects which are felt",
|
||
"Interpretation of the",
|
||
"Effects of",
|
||
"Interpretations based on the condition",
|
||
"Supported houses gain",
|
||
"The immediate focus is",
|
||
"brings house",
|
||
"is read from house",
|
||
"Maha 大运",
|
||
"Antar 大运",
|
||
"Pratyantar 大运",
|
||
"现实场域中阅读",
|
||
"这一现实场域",
|
||
)
|
||
|
||
|
||
EN_FORBIDDEN_CHARS = ("：", "；", "，", "。", "、", "（", "）", "——")
|
||
|
||
|
||
_ZH_REGEX_REPLACEMENTS = tuple(
|
||
(raw, public)
|
||
for raw, public in ZH_TERM_REPLACEMENTS
|
||
if re.fullmatch(r"[A-Za-z0-9_ /:-]+", raw)
|
||
)
|
||
_ZH_LITERAL_REPLACEMENTS = tuple(
|
||
(raw, public)
|
||
for raw, public in ZH_TERM_REPLACEMENTS
|
||
if not re.fullmatch(r"[A-Za-z0-9_ /:-]+", raw)
|
||
)
|
||
_ZH_REGEX_REPLACEMENT_MAP = {raw: public for raw, public in _ZH_REGEX_REPLACEMENTS}
|
||
|
||
|
||
def _zh_regex_body(raw: str) -> str:
|
||
body = re.escape(raw)
|
||
if re.search(r"[A-Za-z]$", raw) and not raw.endswith("s"):
|
||
body += "s?"
|
||
return body
|
||
|
||
|
||
_ZH_REGEX_REPLACEMENT_PATTERN = re.compile(
|
||
r"(?<![A-Za-z0-9_])("
|
||
+ "|".join(
|
||
_zh_regex_body(raw)
|
||
for raw, _public in sorted(_ZH_REGEX_REPLACEMENTS, key=lambda item: len(item[0]), reverse=True)
|
||
)
|
||
+ r")(?![A-Za-z0-9_])"
|
||
)
|
||
|
||
_ZH_NAKSHATRA_GLOSSES = {
|
||
"前阿沙陀": "Purva Ashadha",
|
||
"后阿沙陀": "Uttara Ashadha",
|
||
"后破伽": "Uttara Phalguni",
|
||
"后跋陀罗": "Uttara Bhadrapada",
|
||
"阿湿毗尼": "Ashwini",
|
||
"巴拉尼": "Bharani",
|
||
"基利提卡": "Krittika",
|
||
"罗希尼": "Rohini",
|
||
"鹿首": "Mrigashira",
|
||
"阿尔德拉": "Ardra",
|
||
"普那婆苏": "Punarvasu",
|
||
"普沙": "Pushya",
|
||
"阿什列沙": "Ashlesha",
|
||
"摩伽": "Magha",
|
||
"前破伽": "Purva Phalguni",
|
||
"哈斯塔": "Hasta",
|
||
"吉多罗": "Chitra",
|
||
"斯瓦蒂": "Swati",
|
||
"毗舍佉": "Vishakha",
|
||
"阿奴罗陀": "Anuradha",
|
||
"杰耶什塔": "Jyeshtha",
|
||
"室罗伐那": "Shravana",
|
||
"陀尼湿陀": "Dhanishta",
|
||
"百药宿": "Shatabhisha",
|
||
"前跋陀罗": "Purva Bhadrapada",
|
||
"雷瓦蒂": "Revati",
|
||
}
|
||
_ZH_NAKSHATRA_GLOSS_PATTERN = re.compile(
|
||
"("
|
||
+ "|".join(re.escape(raw) for raw in sorted(_ZH_NAKSHATRA_GLOSSES, key=len, reverse=True))
|
||
+ r")(?![（(])"
|
||
)
|
||
|
||
|
||
def _zh_regex_public(token: str) -> str:
|
||
if token in _ZH_REGEX_REPLACEMENT_MAP:
|
||
return _ZH_REGEX_REPLACEMENT_MAP[token]
|
||
if token.endswith("s") and token[:-1] in _ZH_REGEX_REPLACEMENT_MAP:
|
||
return _ZH_REGEX_REPLACEMENT_MAP[token[:-1]]
|
||
return token
|
||
|
||
|
||
def _replace_zh_regex_terms(markdown: str) -> str:
|
||
def apply(chunk: str) -> str:
|
||
return _ZH_REGEX_REPLACEMENT_PATTERN.sub(
|
||
lambda match: _zh_regex_public(match.group(1)),
|
||
chunk,
|
||
)
|
||
|
||
parts = re.split(r"(`[^`]*`)", markdown)
|
||
return "".join(part if index % 2 else apply(part) for index, part in enumerate(parts))
|
||
|
||
|
||
def normalize_zh_markdown_terms(markdown: str) -> str:
|
||
text = _replace_zh_regex_terms(markdown)
|
||
for raw, public in _ZH_LITERAL_REPLACEMENTS:
|
||
text = text.replace(raw, public)
|
||
text = text.replace("e特殊组合ly", "especially")
|
||
# Repair field-label substitutions that crossed token boundaries in the
|
||
# previous customer pin. These are presentation-only fixes; chart values
|
||
# and source evidence remain unchanged.
|
||
text = text.replace("强est_第", "最强宫")
|
||
text = text.replace("弱est_第", "最弱宫")
|
||
text = text.replace("strongest_house", "最强宫")
|
||
text = text.replace("weakest_house", "最弱宫")
|
||
text = text.replace("7 visible planets occupy exactly 5 distinct signs", "七颗可见行星恰好分布在五个不同星座")
|
||
text = text.replace("Many friends, talkative, skilled in various arts", "人际接触较多，善于表达，具多样艺术或技能倾向")
|
||
text = text.replace("Father died before birth, ancestral curse", "传统规则提示：涉及父系与家族议题，不能据此判断现实经历")
|
||
text = text.replace("Skilled in fine arts, music, dance; cultured and wealthy", "擅长艺术、音乐或舞蹈；重视文化修养与资源积累")
|
||
text = text.replace("Ridiculed by others, mocked, subject to derision", "可能面临误解、嘲讽或评价压力；需结合现实处境核验")
|
||
text = text.replace("Deception, distrust, household/family complications", "信任、家庭关系或居住事务可能较复杂；需结合现实处境核验")
|
||
text = text.replace("rare", "罕见")
|
||
text = text.replace("relationship_observation", "关系观察")
|
||
text = text.replace("solar 瑜伽", "太阳瑜伽")
|
||
text = text.replace("lunar 瑜伽", "月亮瑜伽")
|
||
text = re.sub(r"(\d+)\s+第from\s+月亮", r"从月亮起第\1宫", text)
|
||
text = re.sub(r"\bin\s+(从月亮起第\d+宫)", r"位于\1", text)
|
||
text = text.replace("_aspect_", "宫相位_")
|
||
text = _normalize_zh_bhava_factor_text(text)
|
||
text = text.replace("Bhava 年龄状态 十二宫力量", "Bhava Bala 十二宫力量")
|
||
text = text.replace("Shadbala / Bhava 年龄状态", "Shadbala / Bhava Bala")
|
||
text = text.replace("六维力量 / Bhava 年龄状态", "六维力量 / Bhava Bala")
|
||
text = text.replace("行星s", "行星")
|
||
text = text.replace("星宿 Scheme", "星宿身体对应表")
|
||
text = _normalize_mula_gloss(_restore_zh_nakshatra_glosses(_collapse_duplicate_zh_parentheses(text)))
|
||
text = text.replace("### 是 Solar Return", "### 真实太阳返照")
|
||
text = re.sub(
|
||
r"General effects during the 主大运 of (.+?) are read from the 行星's 自然象征, 落宫, owned houses, 尊贵状态, 星宿, and 功能角色\.",
|
||
r"\1主大运的总体作用，需要从该行星的自然象征、落宫、守护宫、尊贵状态、星宿与功能角色一起阅读。",
|
||
text,
|
||
)
|
||
text = text.replace(
|
||
"Interpretations based on the condition of the 行星 in the birth chart and divisional charts are as follows:",
|
||
"结合本命盘与分盘条件后，可按以下方式细读：",
|
||
)
|
||
text = re.sub(
|
||
r"(.+?)落在(.+?)，首先把(.+?)放到(.+?)这一现实场域中阅读。",
|
||
r"\1落在\2，表示\3会主要通过\4来表现。",
|
||
text,
|
||
)
|
||
text = re.sub(r"第([1-4])足", r"第\1 Pada（星宿四分区）", text)
|
||
text = text.replace("Pada | 速度", "Pada（星宿四分区） | 速度")
|
||
text = _normalize_zh_dasha_prose(text)
|
||
text = _thicken_zh_dasha_density(text)
|
||
text = _normalize_mula_gloss(_restore_zh_nakshatra_glosses(_collapse_duplicate_zh_parentheses(text)))
|
||
return strip_han_plural_s(text)
|
||
|
||
|
||
def _normalize_zh_bhava_factor_text(markdown: str) -> str:
|
||
"""Localize compact Bhava Bala factor formulas in Chinese reports."""
|
||
|
||
text = markdown
|
||
body = r"(?:Sun|Moon|Mars|Mercury|Jupiter|Venus|Saturn|Rahu|Ketu|太阳|月亮|火星|水星|木星|金星|土星|北交点|南交点)"
|
||
text = re.sub(rf"({body})\s+in\s+H(\d+)", r"\1位于第\2宫", text)
|
||
text = re.sub(rf"({body})\s+in\s+(角宫|续宫|果宫)\s+\(H(\d+)\)", r"\1位于\2第\3宫", text)
|
||
text = re.sub(rf"({body})\s+aspects\s+H(\d+)\s+\((\d+)(?:st|nd|rd|th),\s+(自然吉星|自然凶星)\)", r"\1以\3宫相位照第\2宫（\4）", text)
|
||
text = re.sub(rf"({body})\s+aspects\s+H(\d+)\s+\((\d+)(?:st|nd|rd|th)\)", r"\1以\3宫相位照第\2宫", text)
|
||
text = re.sub(r"\((自然吉星|自然凶星)\)", r"（\1）", text)
|
||
text = text.replace("火星宫相位_4", "火星特殊4宫相位")
|
||
text = text.replace("火星宫相位_8", "火星特殊8宫相位")
|
||
text = text.replace("木星宫相位_5", "木星特殊5宫相位")
|
||
text = text.replace("木星宫相位_9", "木星特殊9宫相位")
|
||
text = text.replace("土星宫相位_3", "土星特殊3宫相位")
|
||
text = text.replace("土星宫相位_10", "土星特殊10宫相位")
|
||
return text
|
||
|
||
|
||
def _normalize_mula_gloss(markdown: str) -> str:
|
||
"""Make the Mula gloss idempotent across repeated language passes."""
|
||
|
||
text = markdown
|
||
root_gloss = r"根[，、/]本源"
|
||
text = re.sub(rf"Mula(?:[（(]{root_gloss}[）)])+", "Mula（根、本源）", text)
|
||
text = re.sub(rf"根宿[（(]Mula[（(]{root_gloss}[）)][）)]", "Mula（根、本源）", text)
|
||
text = re.sub(rf"根宿[（(](Mula(?:[（(]{root_gloss}[）)])+)[）)]", "Mula（根、本源）", text)
|
||
return text
|
||
|
||
|
||
def _collapse_duplicate_zh_parentheses(markdown: str) -> str:
|
||
"""Remove duplicated Chinese glosses such as 后破伽（后破伽）."""
|
||
|
||
return re.sub(r"([\u4e00-\u9fff][\u4e00-\u9fff·/-]{0,12})[（(]\1[）)]", r"\1", markdown)
|
||
|
||
|
||
def _restore_zh_nakshatra_glosses(markdown: str) -> str:
|
||
"""Keep the original Sanskrit/English nakshatra label in Chinese reports."""
|
||
|
||
return _ZH_NAKSHATRA_GLOSS_PATTERN.sub(
|
||
lambda match: f"{match.group(1)}（{_ZH_NAKSHATRA_GLOSSES[match.group(1)]}）",
|
||
markdown,
|
||
)
|
||
|
||
|
||
def _thicken_zh_dasha_density(markdown: str) -> str:
|
||
"""Restore reader-facing density for translated AD/PD prose.
|
||
|
||
This adds reading instructions tied to already-present fields. It does not
|
||
introduce new predictions or alter dates.
|
||
"""
|
||
lines = markdown.splitlines()
|
||
out: list[str] = []
|
||
for index, line in enumerate(lines):
|
||
out.append(line)
|
||
lookahead = "\n".join(lines[index + 1:index + 6])
|
||
if "这一子运不是单独结论" in lookahead or "这个次子运只承担短周期细化" in lookahead:
|
||
continue
|
||
ad_match = re.search(
|
||
r"(.+?)主大运中的(.+?)子运，会把(.+?)的自然主题带入当前阶段。",
|
||
line,
|
||
)
|
||
if ad_match:
|
||
md_lord, ad_lord, theme_lord = ad_match.groups()
|
||
out.extend([
|
||
"",
|
||
(
|
||
f"这一子运不是单独结论，而是把{theme_lord}的自然象征放进{md_lord}主大运的背景里筛选。"
|
||
f"阅读时先看{ad_lord}本身的落宫、守护宫、尊贵状态与星宿，再看它和主大运星之间是否互相支持。"
|
||
),
|
||
"",
|
||
(
|
||
"若同一宫位或同一行星在分盘、Ashtakavarga、年度盘和行运中重复出现，"
|
||
"该主题的可见度会提高；若这些层彼此冲突，则应把结果视为阶段性倾向，而不是孤立断语。"
|
||
),
|
||
])
|
||
continue
|
||
pd_match = re.search(
|
||
r"(.+?)子运中的(.+?)次子运，会在(.+?)背景下呈现(.+?)的短周期结果。",
|
||
line,
|
||
)
|
||
if pd_match:
|
||
ad_lord, pd_lord, md_lord, theme_lord = pd_match.groups()
|
||
out.extend([
|
||
"",
|
||
(
|
||
f"这个次子运只承担短周期细化：{pd_lord}会把{theme_lord}的具体征象带入{ad_lord}子运，"
|
||
f"并受{md_lord}主背景限制。"
|
||
),
|
||
"",
|
||
(
|
||
"因此这里优先用于判断事情推进的节奏、触发点和轻重缓急；实际领域仍需回到本命落宫、"
|
||
"分盘重复、年度盘和当前行运共同核对。"
|
||
),
|
||
])
|
||
continue
|
||
return "\n".join(out)
|
||
|
||
|
||
def _normalize_zh_dasha_prose(markdown: str) -> str:
|
||
text = markdown
|
||
replacements = {
|
||
"mind, mother, water, residence, 迁移与出行, public mood, nourishment, fertility, trade, learning, and changeable fortune become active.": "心智、母亲、居住、水象事务、迁移与出行、公众情绪、滋养、生育、贸易、学习与变化中的运势会被启动。",
|
||
"There can be interest in mantra, teachers, sacred learning, art, hospitality, garments, ornaments, land, and watery products.": "这一阶段可能增加对咒语、师长、神圣知识、艺术、服务接待、衣物、饰品、土地与水相关事务的兴趣。",
|
||
"The mind can become lively, sensitive, restless, affectionate, and responsive to family or social approval.": "心绪可能更活跃、敏感、容易波动，也更重视家庭回应与社会认可。",
|
||
"When supported, it brings comfort from home, spouse, children, servants, conveyances, food, clothing, education, fame, and fulfilled desires.": "条件良好时，可带来家庭、伴侣、子女、协助者、交通工具、饮食衣物、教育、名声与愿望满足方面的支持。",
|
||
"New places, cultivation, trade, and public-facing work may become profitable.": "新地点、耕作/经营、贸易与面向公众的工作可能带来收益。",
|
||
"When afflicted, it can show fear, anger, wavering judgment, family strain, maternal concern, contaminated food, 迁移与出行 pressure, and loss of old security.": "受克时，可能表现为恐惧、怒气、判断摇摆、家庭压力、母亲相关担忧、饮食不洁、迁移压力，以及旧有安全感减弱。",
|
||
"Friends may not give full support, and emotional decisions need steadier review.": "朋友支持可能不足，情绪化决定需要更稳妥地复核。",
|
||
"absolute Virupas; precise Sthana/Dig/Kala/Drik; bounded BPHS Chesta": "以绝对 Virupa 计分，包含 Sthana、Dig、Kala、Drik 与受限 BPHS Chesta",
|
||
"fear, anger, wavering judgment, family strain, maternal concern, contaminated food, 迁移与出行 pressure, and loss of old security": "恐惧、怒气、判断摇摆、家庭压力、母亲相关担忧、饮食不洁、迁移压力，以及旧有安全感减弱",
|
||
"unusual openings, foreign benefit, technical or political leverage, and gains through nontraditional channels": "特殊机会、海外或异地收益、技术或权力杠杆，以及非传统渠道带来的收获",
|
||
"fear, bondage, deception, sudden reversals, illness, scandals, and trouble from authorities or hidden enemies": "恐惧、束缚、欺骗、突发反转、疾病、名誉风波，以及来自权威或暗中对手的麻烦",
|
||
"promotion, respect, wealth, grains, clothes, gold, children, good counsel, and fulfillment of aims": "晋升、尊重、财富、物资、衣物、贵金属、子女、良好建议与目标达成",
|
||
"trouble to spouse or children, loss through indulgence, legal worries, fever, or grief from family obligations": "伴侣或子女方面的麻烦、因放纵带来的损耗、法律忧虑、发热或家庭责任带来的忧伤",
|
||
"durable property, work stability, public recognition, gain through labor, and capacity to endure responsibility": "稳定资产、工作稳定、公众认可、辛勤劳动带来的收益，以及承担责任的耐力",
|
||
"pain, quarrels, obstruction, loss of wealth, separation from parents, danger through low morale, and heavy duties": "痛苦、争执、阻碍、财富损耗、与父母分离、士气低落带来的风险，以及沉重职责",
|
||
"knowledge, wealth, garments, jewels, name, ritual merit, useful alliances, and clever problem solving": "知识、财富、衣物、珠宝、名声、仪式功德、有用联盟与灵活的问题解决能力",
|
||
"poor judgment, fever, anxiety, argument, loss through paperwork, and instability in business": "判断不稳、发热、焦虑、争论、文书损耗与商业不稳定",
|
||
"renunciation, spiritual practice, diagnostic skill, hidden knowledge, and the ability to cut through confusion": "放下执着、灵性修持、诊断能力、隐秘知识，以及切断混乱的能力",
|
||
"fear from enemies, loss of reasoning, sudden obstruction, disease, grief, and restless 迁移与出行": "来自对手的恐惧、理性受损、突发阻碍、疾病、忧伤与不安定的迁移出行",
|
||
"spouse happiness, property, conveyance, ornaments, fine food, friendship, and pleasant company": "伴侣愉悦、资产、交通工具、饰品、美食、友谊与愉快陪伴",
|
||
"indulgence, waste, disputes with women or partners, loss through luxury, and ailments connected with reproductive or urinary balance": "放纵、浪费、与女性或伴侣的争执、奢侈带来的损耗，以及生殖或泌尿平衡相关不适",
|
||
"recognition, administrative help, confidence, vehicles, ornaments, and respected duties": "认可、行政助力、自信、交通工具、饰品与受尊重的职责",
|
||
"pressure from government, rivals, fire, theft, father-related strain, feverish conditions, and restlessness": "来自政府/权威、竞争者、火灾、盗损、父亲相关压力、发热状态与内在不安的压力",
|
||
"courage, stamina, property gains, productive labor, victory over enemies, and technical execution": "勇气、体力、资产收益、有效劳动、战胜对手与技术执行力",
|
||
"harsh speech, weapon or fire trouble, stomach ailments, injuries, litigation, and hot-tempered separations": "言语尖锐、武器或火相关麻烦、胃部不适、伤损、诉讼，以及急躁导致的分离",
|
||
"stamina, property, gains, productive labor, victory over enemies": "体力、资产、收益、有效劳动和战胜对手",
|
||
"foreign places, outsiders, ambition, unusual gains, fear, poisons, snakes, politics, sudden turns, obsession, and unconventional paths become prominent.": "异地、外来者、野心、特殊收益、恐惧、毒性/中毒象征、蛇象、政治、突发转折、执念与非传统路径会变得突出。",
|
||
"The period can bring success in ventures, conveyances, garments, distant direction gains, and contact with powerful or foreign circles.": "这一时期可能带来事业尝试、交通工具、衣物、远方收益，以及与有权势或海外/异地圈层接触方面的机会。",
|
||
"If afflicted, it brings defamation, business loss, fever, enemies, anxiety, spouse or child distress, and loss of reputation.": "若受克，可能带来名誉受损、事业损失、发热、对手、焦虑、伴侣或子女方面的压力，以及声望下降。",
|
||
"It favors strategic risk only when facts and ethics are kept clear.": "只有事实清楚、边界正当时，策略性冒险才更有利。",
|
||
"北交点/罗睺-related mantra, restraint, and charity are traditional remedial themes.": "与北交点/罗睺相关的咒语、克制与布施，是传统辅助主题。",
|
||
"labor, delay, servants, masses, endurance, old people, land, minerals, iron, chronic pressure, discipline, and separation themes become prominent.": "劳动、延迟、服务者、大众、耐力、长者、土地、矿物、铁器、长期压力、纪律与分离主题会变得突出。",
|
||
"The period can give property, recognition, steady gains, service authority, and patient achievement after effort.": "这一时期可能带来资产、认可、稳定收益、服务型权责，以及努力之后的耐心成果。",
|
||
"If afflicted, it brings loss of friends, disputes with relatives, fear, confinement, fatigue, rheumatic or digestive trouble, and wandering.": "若受克，可能带来朋友损失、亲属争执、恐惧、受限感、疲惫、风湿或消化问题，以及漂泊。",
|
||
"The middle of the period can be more productive than its beginning or end.": "这一时期的中段往往比开始和结束阶段更容易产生成果。",
|
||
"Traditional balancing themes include service, discipline, humility, and 土星-related charity.": "传统平衡主题包括服务、纪律、谦逊，以及与土星相关的布施。",
|
||
"The period can detach the person from stale ambitions and force a simpler, more inward path.": "这一时期可能使人脱离旧有野心，被迫走向更简单、更内向的路径。",
|
||
"If afflicted, business disturbance, loss of wealth, stomach or eye trouble, fear, conflict, and news of death or separation can appear.": "若受克，可能出现事业扰动、财富损耗、胃部或眼部问题、恐惧、冲突，以及死亡或分离相关消息。",
|
||
"It can produce intermittent gains after pressure or 迁移与出行.": "它可能在压力或迁移之后带来间歇性收益。",
|
||
"Durga worship, protective mantra, and charity are traditional balancing themes.": "杜尔迦崇拜、保护性咒语与布施，是传统平衡主题。",
|
||
"authority, government, 状态, father, medicine, land, fire, command, visibility, and public responsibility become more prominent.": "权威、政府、地位、父亲、医疗、土地、火象事务、指挥权、能见度与公共责任会更突出。",
|
||
"spiritual discipline, mantra, ritual, leadership, and contact with officials or influential people can increase.": "灵性纪律、咒语、仪式、领导力，以及与官员或有影响力人士的接触可能增加。",
|
||
"anxiety, heat, separation from close relatives, disputes with authority, eye, teeth, abdomen, or vitality concerns can also need attention.": "焦虑、热性问题、与近亲分离、和权威争执，以及眼睛、牙齿、腹部或生命力相关议题也需要留意。",
|
||
"It can push philanthropic action, construction, public work, or a clearer place in society.": "它可能推动公益行动、建设事务、公共工作，或让个人在社会中取得更明确的位置。",
|
||
"The person may feel proud, isolated, or forced to leave a familiar place for work or duty.": "当事人可能感到自尊增强但也更孤立，或因工作与职责被迫离开熟悉环境。",
|
||
"energy, courage, land, siblings, weapons, competition, surgery, heat, property disputes, technical action, and decisive breaks become prominent.": "能量、勇气、土地、手足、武器/工具、竞争、手术、热性事务、地产争议、技术行动与果断切割会更突出。",
|
||
"The period increases initiative and can bring land, honors, official recognition, or success through bold effort.": "这一时期会增强主动性，也可能通过大胆行动带来土地、荣誉、官方认可或成功。",
|
||
"teachers, children, wisdom, religion, wealth, counsel, learning, law, protection, ceremonies, and honorable expansion become prominent.": "师长、子女、智慧、宗教、财富、建议、学习、法律、保护、仪式与体面的扩展会更突出。",
|
||
"If afflicted, body pain, family strain, displeasure of authority, missed goals, or loss through poor counsel can appear.": "若受克，可能出现身体疼痛、家庭压力、权威不满、目标落空，或因建议不当导致损失。",
|
||
"education, speech, business, writing, analysis, accounts, friends, trade, negotiation, youth, and skills become prominent.": "教育、言语、商业、写作、分析、账务、朋友、贸易、谈判、年轻人事务与技能会更突出。",
|
||
"separation, austerity, sharp insight, wandering, spiritual pressure, enemies, sudden loss, animals, cuts, and hidden causes become prominent.": "分离、苦修、锐利洞察、漂泊、灵性压力、对手、突发损失、动物、切割伤与隐秘原因会更突出。",
|
||
"comforts, spouse, relationships, ornaments, vehicles, art, luxury, pleasures, agreements, water products, and refined company become prominent.": "舒适、伴侣、关系、饰品、交通工具、艺术、享受、愉悦、协议、水产品与雅致社交会更突出。",
|
||
"The period can bring beauty, garments, jewels, enjoyment, hospitality, marriage themes, and social pleasures.": "这一时期可能带来美感、衣物、珠宝、享受、接待、婚姻主题与社交愉悦。",
|
||
"If afflicted, comforts are disturbed by excess expense, sensual distraction, household conflict, fever, headaches, or relationship strain.": "若受克，舒适感可能被过度开销、感官分心、家庭冲突、发热、头痛或关系压力扰动。",
|
||
}
|
||
if replacements:
|
||
pattern = re.compile("|".join(re.escape(raw) for raw in sorted(replacements, key=len, reverse=True)))
|
||
text = pattern.sub(lambda match: replacements[match.group(0)], text)
|
||
text = re.sub(
|
||
r"Supported houses gain expression through (.+?); strained houses require steadier handling, especially where the same houses repeat in (?:大运|主大运), divisional charts, Ashtakavarga, or the annual chart\.",
|
||
r"受支持的宫位会通过\1获得表达；若同一宫位在大运、分盘、Ashtakavarga 或年度盘中反复承压，则需要更稳妥地处理。",
|
||
text,
|
||
)
|
||
text = re.sub(
|
||
r"When supported, (.+?) (?:gives|brings) (.+?)\.",
|
||
r"条件良好时，\1会带来\2。",
|
||
text,
|
||
)
|
||
text = re.sub(
|
||
r"When strained, (?:it |)(?:can |may |)(?:show|bring) (.+?)\.",
|
||
r"受压时，可能表现为\1。",
|
||
text,
|
||
)
|
||
text = re.sub(
|
||
r"When afflicted, (?:it |)(?:can |may |)(?:show|bring) (.+?)\.",
|
||
r"受克时，可能表现为\1。",
|
||
text,
|
||
)
|
||
text = re.sub(
|
||
r"In the (.+?), (.+?)'s significations give the short-period result inside the (.+?) background\.子运中的(.+?)次子运",
|
||
r"\1子运中的\4次子运，会在\3背景下呈现\2的短周期结果。",
|
||
text,
|
||
)
|
||
text = re.sub(
|
||
r"Consideration: (.+?) is checked from (.+?) against the classical marriage-sensitive houses\. In this chart (.+?) is listed in house (.+?) in (.+?); the detector severity is (.+?)\. Classical reference family: (.+?)\.",
|
||
r"判定方式：\1会从\2出发，检查传统婚恋敏感宫位。本盘中，\3位于第\4宫、\5，检测强度为\6。参考文献族：\7。",
|
||
text,
|
||
)
|
||
text = text.replace(
|
||
"Consideration: this Dosha row is shown only when the local detector returns a chart-specific condition. Classical reference family is attached in the source map.",
|
||
"判定方式：只有本盘检测到对应条件时才列出该 Dosha；对应古典参考族已在资料层登记。",
|
||
)
|
||
text = text.replace(
|
||
"Result: when present, Kuja/Mangala Dosha is read as heat, impatience, conflict, or pressure around partnership handling; when absent or cancelled, the report does not promote it as a dominant relationship obstacle. The result must be read with the seventh house, 金星, Upapada, Navamsha, current 大运, and partner-chart comparison where available.",
|
||
"结果：若火星婚姻煞成立，通常表示关系处理中的热度、急躁、冲突或压力；若不存在或有抵消条件，则不应把它提升为主导关系障碍。该项需要与第七宫、金星、Upapada、Navamsha、当前大运以及可用的伴侣盘一起阅读。",
|
||
)
|
||
text = text.replace(
|
||
"Result: this row contributes a supporting condition and is not promoted over the core chart, 大运, and divisional evidence.",
|
||
"结果：该项只作为辅助条件，不高于本命盘、大运和分盘证据。",
|
||
)
|
||
text = text.replace(
|
||
"Cancellation: no explicit cancellation reasons were returned by the local detector; partner-chart matching remains a separate comparison step.",
|
||
"抵消条件：本地检测器未返回明确抵消原因；伴侣盘匹配仍属于独立比较步骤。",
|
||
)
|
||
text = text.replace(
|
||
"本节按传统大运的总体作用与具体命盘条件两层结构展开，参考：Light on Life An Introduction to the Astrology of India; Predict Effectively through Yogini 大运。",
|
||
"本节按传统大运的总体作用与具体命盘条件两层结构展开，参考《印度占星生命之光》和《Yogini Dasha 实战预测》的结构。",
|
||
)
|
||
text = text.replace(
|
||
"When supported in the chart, this period gives 认可、行政助力、自信、交通工具、饰品与受尊重的职责.",
|
||
"命盘条件良好时，这一阶段可带来认可、行政助力、自信、交通工具、饰品与受尊重的职责。",
|
||
)
|
||
text = text.replace(
|
||
"When supported in the chart, this period gives 体力、资产、收益、有效劳动和战胜对手.",
|
||
"命盘条件良好时，这一阶段可带来体力、资产、收益、有效劳动和战胜对手。",
|
||
)
|
||
text = re.sub(
|
||
r"When supported in the chart, this period gives (.+?)\.",
|
||
r"命盘条件良好时，这一阶段可带来\1。",
|
||
text,
|
||
)
|
||
text = re.sub(
|
||
r"When afflicted, it brings (.+?)\.",
|
||
r"受克时，可能带来\1。",
|
||
text,
|
||
)
|
||
text = re.sub(
|
||
r"If afflicted, (.+?)\.",
|
||
r"若受克，\1。",
|
||
text,
|
||
)
|
||
text = text.replace("Remedies / Supportive 修持s", "传统辅助建议")
|
||
return text
|
||
|
||
|
||
# Fragments left after the longer English glossary. Longer keys are applied first.
|
||
_EN_RESIDUAL_HAN: tuple[tuple[str, str], ...] = (
|
||
("没有候选以吉相位照年盘", "no candidate aspects the annual Lagna by a benefic aspect"),
|
||
("按子运起点星座奇偶", "by the odd or even sign where the sub-period starts"),
|
||
("按七级比较所落星座", "compare the occupied signs across seven levels"),
|
||
("两主分落别的星座", "the two lords fall in other signs"),
|
||
("星座或其主所落星座", "the sign, or the sign its lord occupies"),
|
||
("实际位置判断是否", "judge from the actual position whether"),
|
||
("以吉相位照年盘", "aspect the annual Lagna by a benefic aspect"),
|
||
("不单独增加结论的确定性", "does not by itself make a conclusion more certain"),
|
||
("年数数到该", "the year count reaches that sign"),
|
||
("一律顺行", "always direct"),
|
||
("只倒算计都", "only Ketu is counted backward"),
|
||
("未进打分", "not used in the score"),
|
||
("时间轴结论", "timeline conclusion"),
|
||
("主三角色", "primary triangle role"),
|
||
("七轮裁定", "seven-round decision"),
|
||
("书内分歧", "the book itself disagrees"),
|
||
("待替换为", "still to be replaced by"),
|
||
("取为年主", "is taken as the year lord"),
|
||
("五分力量", "five-fold strength"),
|
||
("五类候选", "five candidate groups"),
|
||
("以凶相位照", "aspect by a malefic aspect"),
|
||
("阶段框架", "phase frame"),
|
||
("起始年龄", "start age"),
|
||
("结束年龄", "end age"),
|
||
("六重力量", "six-fold strength"),
|
||
("矩阵源数据", "matrix source"),
|
||
("相位矩阵", "aspect matrix"),
|
||
("灵魂使命", "soul aim"),
|
||
("核心自我", "core self"),
|
||
("人生最高目标", "highest aim"),
|
||
("主要谋士", "main advisor"),
|
||
("权力代理", "delegated authority"),
|
||
("兄弟姐妹", "siblings"),
|
||
("冒险精神", "appetite for risk"),
|
||
("家庭根基", "home base"),
|
||
("情感安全感", "emotional security"),
|
||
("祖先业力", "ancestral pattern"),
|
||
("传统传承", "inherited tradition"),
|
||
("智能成果", "crafted results"),
|
||
("竞争对手", "rivals"),
|
||
("转化力量", "capacity for change"),
|
||
("配偶特质", "spouse traits"),
|
||
("伴侣关系", "partnership"),
|
||
("书例校准", "book-example calibration"),
|
||
("八分法", "eightfold division"),
|
||
("要素数量", "factor count"),
|
||
("要素总数", "factor total"),
|
||
("综合性质", "overall nature"),
|
||
("基本年数", "base years"),
|
||
("并列参考", "side reference"),
|
||
("双主星", "dual lords"),
|
||
("子运方向", "sub-period direction"),
|
||
("身份按同", "identity follows the same"),
|
||
("明显迹象", "a clear indication"),
|
||
("严重程度", "severity"),
|
||
("轴线之间", "between the axis"),
|
||
("颗行星", "planets"),
|
||
("高峰期", "peak phase"),
|
||
("下降期", "setting phase"),
|
||
("最困难", "most difficult"),
|
||
("需结合", "read together with"),
|
||
("灵魂星", "soul planet"),
|
||
("兄弟星", "sibling planet"),
|
||
("母亲星", "mother planet"),
|
||
("父亲星", "father planet"),
|
||
("子女星", "child planet"),
|
||
("障碍星", "obstacle planet"),
|
||
("配偶星", "spouse planet"),
|
||
("旧算法", "previous algorithm"),
|
||
("按原书", "per the book"),
|
||
("起运", "period start"),
|
||
("从主", "from the lord"),
|
||
("级取", "the level selects"),
|
||
("两主", "two lords"),
|
||
("等分", "equal parts"),
|
||
("未采用", "not used"),
|
||
("星座奇偶", "odd or even sign"),
|
||
("的子运", "sub-period"),
|
||
("待评估", "not yet assessed"),
|
||
("进行medium", "underway"),
|
||
("当before", "current "),
|
||
("原始值", "raw value"),
|
||
("主层", "main level"),
|
||
("子层", "sub level"),
|
||
("年数", "years"),
|
||
("主星", "lord"),
|
||
("序号", "index"),
|
||
("起始", "start"),
|
||
("结束", "end"),
|
||
("星座", "sign"),
|
||
("相位", "aspect"),
|
||
("年度", "annual"),
|
||
("细项", "detail"),
|
||
("年返", "solar return"),
|
||
("摘要", "summary"),
|
||
("项目", "item"),
|
||
("数值", "value"),
|
||
("方法", "method"),
|
||
("校验", "check"),
|
||
("辅助", "supporting"),
|
||
("算法", "algorithm"),
|
||
("并列", "listed alongside"),
|
||
("顺序", "order"),
|
||
("修正", "adjustment"),
|
||
("最终", "final"),
|
||
("正文", "body text"),
|
||
("阶段", "phase"),
|
||
("是否", "whether"),
|
||
("只有", "only"),
|
||
("特殊", "special"),
|
||
("方向", "direction"),
|
||
("勇气", "courage"),
|
||
("母亲", "mother"),
|
||
("父亲", "father"),
|
||
("子女", "children"),
|
||
("创造力", "creativity"),
|
||
("学生", "students"),
|
||
("障碍", "obstacles"),
|
||
("质量", "quality"),
|
||
("顺行", "direct"),
|
||
("逆行", "retrograde"),
|
||
("比较", "compare"),
|
||
("另一", "another"),
|
||
("部分", "partial"),
|
||
("进行", "in progress"),
|
||
("占据planet尊贵", "occupied planet dignity"),
|
||
("占据planet数", "occupied planet count"),
|
||
("partial减weak", "partially reduced"),
|
||
("成立条件", "conditions"),
|
||
("不in煞", "not in a malefic house"),
|
||
("迹象", "indication"),
|
||
("相邻", "adjacent"),
|
||
("占据", "occupies"),
|
||
("尊贵", "dignity"),
|
||
("克", "restrains"),
|
||
("其", " its "),
|
||
("减", "reduced"),
|
||
("最", "most "),
|
||
("条", "items"),
|
||
("的", " of "),
|
||
("不", "not "),
|
||
("吉", "benefic"),
|
||
("数", "count"),
|
||
("煞", "malefic"),
|
||
("看", "see"),
|
||
("起", "from"),
|
||
("版", "edition"),
|
||
("级", "level"),
|
||
("主", "lord"),
|
||
("期", "phase"),
|
||
("星", "planet"),
|
||
("度", "degree"),
|
||
("从", "from"),
|
||
("取", "take"),
|
||
("所", "at"),
|
||
("较", "comparatively"),
|
||
("当", "when"),
|
||
("按", "by"),
|
||
("有", "present"),
|
||
("无", "absent"),
|
||
("表", "table"),
|
||
)
|
||
|
||
|
||
def apply_en_residual_han(markdown: str) -> str:
|
||
"""Translate Han fragments that survive the longer English glossary."""
|
||
text = markdown
|
||
for raw, public in sorted(_EN_RESIDUAL_HAN, key=lambda item: len(item[0]), reverse=True):
|
||
text = text.replace(raw, public)
|
||
return text
|
||
|
||
|
||
def normalize_en_markdown_terms(markdown: str) -> str:
|
||
text = markdown.replace("（", "(").replace("）", ")").replace("、", ", ")
|
||
text = (
|
||
text.replace("dt_ut", "UTC time")
|
||
.replace("dt_local", "Local time")
|
||
.replace("sun_lon", "Sun longitude")
|
||
.replace("year_lord", "Year lord")
|
||
.replace("field_status", "Field status")
|
||
.replace("muntha_house", "Muntha house")
|
||
.replace("muntha_sign", "Muntha sign")
|
||
.replace("muntha_lord", "Muntha lord")
|
||
)
|
||
text = re.sub(
|
||
r"\b(Mars|Jupiter|Venus|Saturn|Mercury|Sun|Moon|Rahu|Ketu)(\d{1,2})\b",
|
||
r"\1 \2",
|
||
text,
|
||
)
|
||
return apply_en_residual_han(_thicken_en_dasha_density(text))
|
||
|
||
|
||
def _thicken_en_dasha_density(markdown: str) -> str:
|
||
"""Add chapter-level AD context without repeating boilerplate on every PD row."""
|
||
|
||
lines = markdown.splitlines()
|
||
out: list[str] = []
|
||
current_md = None
|
||
ad_context_added = False
|
||
for index, line in enumerate(lines):
|
||
md_heading = re.match(r"^#{2,4}\s+(.+?\bMaha Dasha\b.*)$", line)
|
||
if md_heading:
|
||
next_md = md_heading.group(1)
|
||
if next_md != current_md:
|
||
current_md = next_md
|
||
ad_context_added = False
|
||
out.append(line)
|
||
lookahead = "\n".join(lines[index + 1:index + 6])
|
||
if (
|
||
"This Antar Dasha is not read as a standalone verdict" in lookahead
|
||
or "This Pratyantar Dasha is the short-cycle refinement" in lookahead
|
||
):
|
||
continue
|
||
ad_match = re.search(
|
||
r"The Antar Dasha of (.+?) activates (.+?)'s natural themes inside the broader Maha Dasha of (.+?)\.",
|
||
line,
|
||
)
|
||
if ad_match and not ad_context_added:
|
||
ad_lord, theme_lord, md_lord = ad_match.groups()
|
||
out.extend([
|
||
"",
|
||
(
|
||
f"This Antar Dasha is not read as a standalone verdict. It places {theme_lord}'s "
|
||
f"natural significations inside the background of the {md_lord} Maha Dasha, then "
|
||
f"filters them through {ad_lord}'s house placement, house ownership, dignity, "
|
||
"nakshatra lord, conjunctions, and divisional-chart repetition."
|
||
),
|
||
"",
|
||
(
|
||
"When the same planet or house repeats through divisional charts, Ashtakavarga, "
|
||
"annual factors, and transits, the theme becomes more visible. When those layers "
|
||
"conflict, the result should be read as a staged tendency rather than an isolated statement."
|
||
),
|
||
])
|
||
ad_context_added = True
|
||
continue
|
||
pd_match = re.search(
|
||
r"In the Pratyantar Dasha of (.+?) in the Antar Dasha of (.+?), (.+?)'s significations give the short-period result inside the (.+?) background\.",
|
||
line,
|
||
)
|
||
if pd_match:
|
||
# The row already contains the concrete PD lord and timing context.
|
||
# Keep it, but do not append the same methodology paragraph per node.
|
||
continue
|
||
return "\n".join(out)
|
||
|
||
|
||
def language_quality_receipt(markdown: str, *, language: str) -> dict[str, Any]:
|
||
violations: list[str] = []
|
||
if language == "en":
|
||
chinese_chars = len(re.findall(r"[\u4e00-\u9fff]", markdown))
|
||
if chinese_chars:
|
||
violations.append(f"chinese_characters:{chinese_chars}")
|
||
for char in EN_FORBIDDEN_CHARS:
|
||
if char in markdown:
|
||
violations.append(f"fullwidth_punctuation:{char}")
|
||
else:
|
||
for phrase in ZH_FORBIDDEN_MIXED_PHRASES:
|
||
if phrase in markdown:
|
||
violations.append(f"mixed_template_phrase:{phrase}")
|
||
suspicious_lines: list[str] = []
|
||
for line_no, line in enumerate(markdown.splitlines(), 1):
|
||
if line.lstrip().startswith("|"):
|
||
continue
|
||
if not re.search(r"[\u4e00-\u9fff]", line):
|
||
continue
|
||
words = re.findall(r"\b[A-Za-z][A-Za-z/_-]{2,}\b", line)
|
||
non_allowed = [word for word in words if word not in ZH_ALLOWED_LATIN_TOKENS]
|
||
if len(non_allowed) >= 5:
|
||
suspicious_lines.append(f"{line_no}:{','.join(non_allowed[:8])}")
|
||
if len(suspicious_lines) >= 20:
|
||
break
|
||
if suspicious_lines:
|
||
violations.append("mixed_english_dense_lines:" + ";".join(suspicious_lines))
|
||
return {
|
||
"schema": "pl9.language_quality_receipt.v1",
|
||
"language": language,
|
||
"status": "pass" if not violations else "fail",
|
||
"violations": violations,
|
||
}
|