当前位置：首页 > news >正文

python fonttools字体多语言解析

news 2025/7/17 5:24:28

1.py

from fontTools.ttLib import TTFont# 语言ID映射表（部分常用）
lang_map = {# Windows Language IDs (LCID)0x0000: 'default',0x0409: 'en',           # English (US)0x0809: 'en-GB',        # English (UK)0x0C09: 'en-AU',        # English (Australia)0x1009: 'en-CA',        # English (Canada)0x1409: 'en-NZ',        # English (New Zealand)0x0404: 'zh-Hant',      # Chinese Traditional (Taiwan)0x0021: 'zh-Hans',      # Chinese Simplified0x0804: 'zh-Hans',      # Chinese Simplified (PRC)0x0C04: 'zh-Hant-HK',   # Chinese Traditional (Hong Kong)0x1004: 'zh-Hant-MO',   # Chinese Traditional (Macao)0x1404: 'zh-Hans-SG',   # Chinese Simplified (Singapore)0x0411: 'ja',           # Japanese (Japan)0x0412: 'ko',           # Korean (Korea)0x040C: 'fr',           # French (France)0x080C: 'fr-BE',        # French (Belgium)0x0C0C: 'fr-CA',        # French (Canada)0x100C: 'fr-CH',        # French (Switzerland)0x0407: 'de',           # German (Germany)0x0C07: 'de-AT',        # German (Austria)0x1007: 'de-CH',        # German (Switzerland)0x040A: 'es',           # Spanish (Spain, Modern Sort)0x080A: 'es-MX',        # Spanish (Mexico)0x0C0A: 'es-ES',        # Spanish (Spain, Traditional Sort)0x0413: 'nl',           # Dutch (Netherlands)0x0813: 'nl-BE',        # Dutch (Belgium)0x0414: 'no',           # Norwegian Bokmål (Norway)0x0814: 'nn-NO',        # Norwegian Nynorsk (Norway)0x0415: 'pl',           # Polish (Poland)0x0416: 'pt-BR',        # Portuguese (Brazil)0x0816: 'pt',           # Portuguese (Portugal)0x0418: 'ro',           # Romanian (Romania)0x0419: 'ru',           # Russian (Russia)0x041B: 'sk',           # Slovak (Slovakia)0x0424: 'sl',           # Slovenian (Slovenia)0x040E: 'hu',           # Hungarian (Hungary)0x042E: 'hr',           # Croatian (Croatia)0x041F: 'tr',           # Turkish (Turkey)0x0441: 'ar-SA',        # Arabic (Saudi Arabia)0x0436: 'af',           # Afrikaans (South Africa)0x043E: 'ms',           # Malay (Malaysia)0x0439: 'hi',           # Hindi (India)0x043C: 'th',           # Thai (Thailand)0x0450: 'vi',           # Vietnamese (Vietnam)0x045A: 'hy',           # Armenian (Armenia)0x046B: 'bn',           # Bengali (India)0x0457: 'ml',           # Malayalam (India)0x0449: 'mr',           # Marathi (India)0x044C: 'ta',           # Tamil (India)0x044E: 'te',           # Telugu (India)0x047A: 'uz',           # Uzbek (Latin)0x042D: 'eu',           # Basque (Basque)0x042C: 'az',           # Azerbaijani (Latin)0x0423: 'be',           # Belarusian (Belarus)0x040D: 'he',           # Hebrew (Israel)0x041D: 'sv',           # Swedish (Sweden)0x041E: 'th',           # Thai (Thailand)0x0425: 'et',           # Estonian (Estonia)0x0426: 'fi',           # Finnish (Finland)0x042F: 'mk',           # Macedonian (North Macedonia)0x043F: 'kk',           # Kazakh (Kazakhstan)0x0443: 'mn',           # Mongolian (Mongolia)0x0444: 'ne',           # Nepali (Nepal)0x0445: 'pa',           # Punjabi (India)0x0446: 'gu',           # Gujarati (India)0x0447: 'or',           # Odia (India)0x044A: 'si',           # Sinhala (Sri Lanka)0x044B: 'lo',           # Lao (Laos)0x044D: 'bo',           # Tibetan (PRC)0x044F: 'sa',           # Sanskrit (India)0x0451: 'ky',           # Kyrgyz (Kyrgyzstan)0x0453: 'ka',           # Georgian (Georgia)0x0454: 'am',           # Amharic (Ethiopia)0x045C: 'ug',           # Uyghur (PRC)0x045D: 'gl',           # Galician (Galicia)0x045E: 'kok',          # Konkani (India)0x045F: 'syr',          # Syriac (Syria)0x0460: 'dv',           # Divehi (Maldives)0x0461: 'chr',          # Cherokee (United States)0x0462: 'iu',           # Inuktitut (Canadian Aboriginal Syllabics)0x0463: 'dz',           # Dzongkha (Bhutan)0x0464: 'km',           # Khmer (Cambodia)0x0465: 'lo_LA',        # Lao (Laos)0x0466: 'my',           # Burmese (Myanmar)0x0467: 'as',           # Assamese (India)0x0468: 'ml_IN',        # Malayalam (India)0x0469: 'kn',           # Kannada (India)0x046A: 'te_IN',        # Telugu (India)0x046B: 'bn_BD',        # Bengali (Bangladesh)0x046C: 'bn_IN',        # Bengali (India)0x046D: 'tzm',          # Tamazight (Berber) (Morocco)0x046E: 'ks',           # Kashmiri (India)0x046F: 'sd',           # Sindhi (Pakistan)0x0470: 'farsi',        # Farsi (Persian) (Iran)0x0471: 'ps',           # Pashto (Afghanistan)0x0472: 'ff',           # Fulah (Senegal)0x0473: 'ha',           # Hausa (Nigeria)0x0474: 'yo',           # Yoruba (Nigeria)0x0475: 'ig',           # Igbo (Nigeria)0x0476: 'kr',           # Kanuri (Nigeria)0x0477: 'om',           # Oromo (Ethiopia)0x0478: 'ti',           # Tigrinya (Ethiopia)0x0479: 'sn',           # Shona (Zimbabwe)0x047A: 'uz_UZ',        # Uzbek (Latin)0x047B: 'gl_ES',        # Galician (Spain)0x047C: 'af_ZA',        # Afrikaans (South Africa)0x047D: 'ka_GE',        # Georgian (Georgia)
}# Map keyed by platformID, then platEncID, then possibly langID
# Macintosh
# See
# https://github.com/fonttools/fonttools/issues/236
# 0: {  # Macintosh, platEncID==0, keyed by langID# 15: "mac_iceland",# 17: "mac_turkish",# 18: "mac_croatian",# 24: "mac_latin2",# 25: "mac_latin2",# 26: "mac_latin2",# 27: "mac_latin2",# 28: "mac_latin2",# 36: "mac_latin2",# 37: "mac_romanian",# 38: "mac_latin2",# 39: "mac_latin2",# 40: "mac_latin2",# Ellipsis: "mac_roman",  # Other# platformID + encodingID -> 编码器名称
encoding_map = {# Unicode Platform (platformID = 0)(0, 0): 'Unicode 1.0 semantics[utf_16_be]',(0, 1): 'Unicode 1.1 semantics[utf_16_be]',(0, 2): 'ISO 10646:1993 semantics[utf_16_be]',(0, 3): 'Unicode 2.0 BMP only[utf_16_be]',(0, 4): 'Unicode 2.0 full repertoire[utf_16_be]',(0, 5): 'Unicode for ISO 10646:1997[utf_16_be]',(0, 6): 'Unicode Variation Sequences[utf_16_be]',(0, 7): 'Unicode full repertoire[utf_16_be]',# Macintosh Platform (platformID = 1)(1, 0): 'Mac Roman',(1, 1): 'x_mac_japanese_ttx[shift_jis]',(1, 2): 'x_mac_trad_chinese_ttx[big5]',(1, 3): 'x_mac_korean_ttx[euc_kr]',(1, 4): 'Mac Arabic',(1, 5): 'Mac Hebrew',(1, 6): 'Mac Greek',(1, 7): 'Mac Cyrillic',(1, 8): 'Mac Devanagari',(1, 9): 'Mac Bengali',(1, 10): 'Mac Gurmukhi',(1, 11): 'Mac Gujarati',(1, 12): 'Mac Oriya',(1, 13): 'Mac Tamil',(1, 14): 'Mac Telugu',(1, 15): 'Mac Kannada',(1, 16): 'Mac Malayalam',(1, 17): 'Mac Sinhalese',(1, 18): 'Mac Burmese',(1, 19): 'Mac Khmer',(1, 20): 'Mac Thai',(1, 21): 'Mac Laotian',(1, 22): 'Mac Georgian',(1, 23): 'Mac Armenian',(1, 24): 'Mac Chinese Simplified',(1, 25): 'x_mac_simp_chinese_ttx[gb2312]',(1, 26): 'Mac Mongolian',(1, 27): 'Mac Geez',(1, 28): 'Mac Slavic',(1, 29): 'mac_latin2',(1, 30): 'Mac Sindhi',(1, 31): 'Mac Uninterpreted',(1, 35): 'mac_turkish',(1, 37): 'mac_iceland',# iso(2, 0): 'ascii',(2, 1): 'utf_16_be',(2, 2): 'latin1',# Windows Platform (platformID = 3)(3, 0): 'Windows Symbol[utf_16_be]',(3, 1): 'Windows Unicode BMP[utf_16_be]',(3, 2): 'Windows ShiftJIS[shift_jis]',(3, 3): 'Windows PRC[gb2312]',(3, 4): 'Windows Big5[big5]',(3, 5): 'Windows Wansung[euc_kr]',(3, 6): 'Windows Johab[johab]',(3, 7): 'Windows Reserved 7',(3, 8): 'Windows Reserved 8',(3, 9): 'Windows Reserved 9',(3, 10): 'Windows Unicode UCS-4[utf_16_be]',(3, 11): 'Windows Reserved 11',(3, 12): 'Windows Reserved 12',(3, 13): 'Windows Reserved 13',(3, 14): 'Windows Reserved 14',(3, 15): 'Windows Reserved 15',(3, 16): 'Windows OEM Character Set',(3, 17): 'Windows Reserved 17',
}def get_font_names(font_path):"""提取字体文件中的名称信息，支持中文解析并映射 encoding_id 到可读编码名称。Args:font_path: 字体文件的路径。Returns:一个字典，包含字体名称信息。"""try:font = TTFont(font_path)name_table = font['name']names = {}for record in name_table.names:name_id = record.nameIDplatform_id = record.platformIDencoding_id = record.platEncIDlanguage_id = record.langIDlang_key = lang_map.get(language_id, f"0x{language_id:04X}")try:text = record.toUnicode()except UnicodeDecodeError:try:# 尝试手动使用 UTF-16BE 解码（常见于 Mac 平台）text = record.string.decode('utf-16-be')except Exception as e:text = f"[Decoding error: {e}]"if name_id not in names:names[name_id] = {}key = (platform_id, encoding_id, lang_key)names[name_id][key] = textname_map = {1: 'familyName',2: 'styleName',4: 'fullName',6: 'postScriptName',16: 'preferredFamilyName',   #TYPOGRAPHIC_FAMILY 17: 'preferredSubfamilyName',  #TYPOGRAPHIC_SUBFAMILY}result = {}for name_id, name_type in name_map.items():if name_id in names:result[name_type] = names[name_id]return resultexcept Exception as e:print(f"Error processing font: {e}")return Nonefinally:if 'font' in locals():font.close()# 示例
fontPath = "C:\\AlibabaPuHuiTi.ttf"
font_names = get_font_names(fontPath)if font_names:for name_type, name_values in font_names.items():print(f"Name Type: {name_type}")for (platform_id, encoding_id, lang), text in name_values.items():encoding_desc = encoding_map.get((platform_id, encoding_id), f"Unknown ({platform_id}, {encoding_id})")print(f"  - Lang: {lang} | Encoding: {encoding_desc}: {text}")
else:print("无法提取字体名称")

运行

pip install fonttools
python parse.py

结果

Name Type: familyName
- Lang: default | Encoding: Mac Roman: Alibaba PuHuiTi 2.0
- Lang: zh-Hans | Encoding: x_mac_simp_chinese_ttx[gb2312]: 阿里巴巴普惠体 2.0
- Lang: en | Encoding: Windows Unicode BMP[utf_16_be]: Alibaba PuHuiTi 2.0 55 Regular
- Lang: zh-Hans | Encoding: Windows Unicode BMP[utf_16_be]: 阿里巴巴普惠体 2.0 55 Regular
Name Type: styleName
- Lang: default | Encoding: Mac Roman: 55 Regular
- Lang: zh-Hans | Encoding: x_mac_simp_chinese_ttx[gb2312]: 55 Regular
- Lang: en | Encoding: Windows Unicode BMP[utf_16_be]: Regular
- Lang: zh-Hans | Encoding: Windows Unicode BMP[utf_16_be]: Regular
Name Type: fullName
- Lang: default | Encoding: Mac Roman: Alibaba PuHuiTi 2 55 Regular
- Lang: zh-Hans | Encoding: x_mac_simp_chinese_ttx[gb2312]: 阿里巴巴普惠体 2 55 Regular
- Lang: en | Encoding: Windows Unicode BMP[utf_16_be]: Alibaba PuHuiTi 2 55 Regular
- Lang: zh-Hans | Encoding: Windows Unicode BMP[utf_16_be]: 阿里巴巴普惠体 2 55 Regular
Name Type: postScriptName
- Lang: default | Encoding: Mac Roman: AlibabaPuHuiTi_2_55_Regular
- Lang: en | Encoding: Windows Unicode BMP[utf_16_be]: AlibabaPuHuiTi_2_55_Regular
Name Type: preferredFamilyName
- Lang: en | Encoding: Windows Unicode BMP[utf_16_be]: Alibaba PuHuiTi 2.0
- Lang: zh-Hans | Encoding: Windows Unicode BMP[utf_16_be]: 阿里巴巴普惠体 2.0
Name Type: preferredSubfamilyName
- Lang: en | Encoding: Windows Unicode BMP[utf_16_be]: 55 Regular
- Lang: zh-Hans | Encoding: Windows Unicode BMP[utf_16_be]: 55 Regular

2.命令行

ttx -t name -o name_table.xml "C:\\AlibabaPuHuiTi-2-55-Regular_1.ttf"

结果

<?xml version="1.0" encoding="UTF-8"?>
<ttFont sfntVersion="\x00\x01\x00\x00" ttLibVersion="4.58">

<name>
<namerecord nameID="0" platformID="1" platEncID="0" langID="0x0" unicode="True">
Copyright ?2020-2021 Alibaba (China) Co., Ltd. All rights reserved.
</namerecord>
<namerecord nameID="1" platformID="1" platEncID="0" langID="0x0" unicode="True">
Alibaba PuHuiTi 2.0
</namerecord>
<namerecord nameID="2" platformID="1" platEncID="0" langID="0x0" unicode="True">
55 Regular
</namerecord>
<namerecord nameID="3" platformID="1" platEncID="0" langID="0x0" unicode="True">
Hanyi Alibaba-PuHuiTi-2-55-Regular v2.00
</namerecord>
<namerecord nameID="4" platformID="1" platEncID="0" langID="0x0" unicode="True">
Alibaba PuHuiTi 2 55 Regular
</namerecord>
<namerecord nameID="5" platformID="1" platEncID="0" langID="0x0" unicode="True">
Version 2.00
</namerecord>
<namerecord nameID="6" platformID="1" platEncID="0" langID="0x0" unicode="True">
AlibabaPuHuiTi_2_55_Regular
</namerecord>
<namerecord nameID="7" platformID="1" platEncID="0" langID="0x0" unicode="True">
Alibaba is a trademark of Alibaba Group Holding Limited.
</namerecord>
<namerecord nameID="8" platformID="1" platEncID="0" langID="0x0" unicode="True">
Alibaba Design;Hanyi Fonts
</namerecord>
<namerecord nameID="10" platformID="1" platEncID="0" langID="0x0" unicode="True">
GB18030-2000
</namerecord>
<namerecord nameID="0" platformID="1" platEncID="25" langID="0x21" unicode="True">
(c) 2020-2021 阿里巴巴（中国）有限公司，版权所有
</namerecord>
<namerecord nameID="1" platformID="1" platEncID="25" langID="0x21" unicode="True">
阿里巴巴普惠体 2.0
</namerecord>
<namerecord nameID="2" platformID="1" platEncID="25" langID="0x21" unicode="True">
55 Regular
</namerecord>
<namerecord nameID="4" platformID="1" platEncID="25" langID="0x21" unicode="True">
阿里巴巴普惠体 2 55 Regular
</namerecord>
<namerecord nameID="7" platformID="1" platEncID="25" langID="0x21" unicode="True">
阿里巴巴、Alibaba是阿里巴巴集团在中国及其他国家或地区的商标或注册商标
</namerecord>
<namerecord nameID="8" platformID="1" platEncID="25" langID="0x21" unicode="True">
Alibaba Design；汉仪字库
</namerecord>
<namerecord nameID="10" platformID="1" platEncID="25" langID="0x21" unicode="True">
GB18030-2000
</namerecord>
<namerecord nameID="0" platformID="3" platEncID="1" langID="0x409">
Copyright © 2020-2021 Alibaba (China) Co., Ltd. All rights reserved.
</namerecord>
<namerecord nameID="1" platformID="3" platEncID="1" langID="0x409">
Alibaba PuHuiTi 2.0 55 Regular
</namerecord>
<namerecord nameID="2" platformID="3" platEncID="1" langID="0x409">
Regular
</namerecord>
<namerecord nameID="3" platformID="3" platEncID="1" langID="0x409">
Hanyi Alibaba-PuHuiTi-2-55-Regular v2.00
</namerecord>
<namerecord nameID="4" platformID="3" platEncID="1" langID="0x409">
Alibaba PuHuiTi 2 55 Regular
</namerecord>
<namerecord nameID="5" platformID="3" platEncID="1" langID="0x409">
Version 2.00
</namerecord>
<namerecord nameID="6" platformID="3" platEncID="1" langID="0x409">
AlibabaPuHuiTi_2_55_Regular
</namerecord>
<namerecord nameID="7" platformID="3" platEncID="1" langID="0x409">
Alibaba is a trademark of Alibaba Group Holding Limited.
</namerecord>
<namerecord nameID="8" platformID="3" platEncID="1" langID="0x409">
Alibaba Design;Hanyi Fonts
</namerecord>
<namerecord nameID="10" platformID="3" platEncID="1" langID="0x409">
GB18030-2000
</namerecord>
<namerecord nameID="16" platformID="3" platEncID="1" langID="0x409">
Alibaba PuHuiTi 2.0
</namerecord>
<namerecord nameID="17" platformID="3" platEncID="1" langID="0x409">
55 Regular
</namerecord>
<namerecord nameID="0" platformID="3" platEncID="1" langID="0x804">
(c) 2020-2021 阿里巴巴（中国）有限公司，版权所有
</namerecord>
<namerecord nameID="1" platformID="3" platEncID="1" langID="0x804">
阿里巴巴普惠体 2.0 55 Regular
</namerecord>
<namerecord nameID="2" platformID="3" platEncID="1" langID="0x804">
Regular
</namerecord>
<namerecord nameID="4" platformID="3" platEncID="1" langID="0x804">
阿里巴巴普惠体 2 55 Regular
</namerecord>
<namerecord nameID="7" platformID="3" platEncID="1" langID="0x804">
阿里巴巴、Alibaba是阿里巴巴集团在中国及其他国家或地区的商标或注册商标
</namerecord>
<namerecord nameID="8" platformID="3" platEncID="1" langID="0x804">
Alibaba Design；汉仪字库
</namerecord>
<namerecord nameID="10" platformID="3" platEncID="1" langID="0x804">
GB18030-2000
</namerecord>
<namerecord nameID="16" platformID="3" platEncID="1" langID="0x804">
阿里巴巴普惠体 2.0
</namerecord>
<namerecord nameID="17" platformID="3" platEncID="1" langID="0x804">
55 Regular
</namerecord>
</name>

</ttFont>