iso-langcodes 1.0.0__py3-none-any.whl

iso_langcodes/__init__.py

@@ -0,0 +1,16 @@
+"""
+langcodes - Python modules for working with language codes, language groups and language scripts.
+
+This package provides:
+- ISO 639-3: conversion between ISO language codes
+- ISO 639-5: language groups and families according to ISO 639-5
+- ISO 15924: language scripts and their connection to languages
+"""
+
+from . import iso639_3
+from . import iso639_5
+from . import iso15924
+
+__version__ = "1.0.0"
+__author__ = "Joerg Tiedemann"
+__all__ = ["iso639_3", "iso639_5", "iso15924"]

iso_langcodes/cli/__init__.py

@@ -0,0 +1 @@
+"""CLI package for langcodes."""

iso_langcodes/cli/iso639.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+"""
+iso639 - a simple script to convert language codes.
+
+Usage: iso639 [-2|-3|-m|-n|-k] [langcode]*
+
+Convert to 3-letter-code if 2-letter code is given and vice versa.
+-2 ... print 2-letter code (even if the input is a 2-letter code)
+-3 ... print 3-letter code (even if the input is a 3-letter code)
+-m ... print macro language instead of local language variants
+-n ... don't print a final new-line
+-k ... keep original code if no mapping is found
+-p ... convert language pairs
+-P ... convert language pairs and sort alphabetically
+"""
+
+import argparse
+import sys
+
+from .. import iso639_3
+
+
+def convert_pairs(type_, langs, sorted_, keep):
+    """Convert language pairs instead of single language codes."""
+    converted = [iso639_3.convert_iso639(type_, lang, keep) for lang in langs.split('-')]
+    if sorted_:
+        converted = sorted(converted)
+    return '-'.join(converted)
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Convert language codes')
+    parser.add_argument('-2', '--iso639-1', action='store_true', help='convert to two-letter code (ISO 639-1)')
+    parser.add_argument('-3', '--iso639-3', action='store_true', help='convert to three-letter code (ISO 639-3)')
+    parser.add_argument('-m', '--macro', action='store_true', help='convert to macro language')
+    parser.add_argument('-n', '--no-newline', action='store_true', help="don't print a final new line")
+    parser.add_argument('-k', '--keep', action='store_true', help='keep original code if no mapping is found')
+    parser.add_argument('-p', '--pairs', action='store_true', help='convert language pairs')
+    parser.add_argument('-P', '--pairs-sorted', action='store_true', help='convert language pairs and sort alphabetically')
+    parser.add_argument('langcodes', nargs='*', help='language codes to convert')
+
+    args = parser.parse_args()
+
+    if args.iso639_1:
+        type_ = 'iso639-1'
+    elif args.iso639_3:
+        type_ = 'iso639-3'
+    elif args.macro:
+        type_ = 'macro'
+    else:
+        type_ = 'name'
+
+    if args.pairs or args.pairs_sorted:
+        converted = [convert_pairs(type_, lang, args.pairs_sorted, args.keep) for lang in args.langcodes]
+    else:
+        converted = [iso639_3.convert_iso639(type_, lang, args.keep) for lang in args.langcodes]
+
+    if type_ == 'name' and converted:
+        print('"' + '" "'.join(converted) + '"', end='')
+    else:
+        print(' '.join(converted), end='')
+
+    if not args.no_newline:
+        print()
+
+
+if __name__ == '__main__':
+    main()

iso_langcodes/cli/langglottolog.py

@@ -0,0 +1,58 @@
+#!/usr/bin/env python3
+"""
+langglottolog - convert between ISO 639-5 codes and Glottolog codes.
+
+Usage: langglottolog [OPTIONS] CODE*
+
+Options:
+  -h: help
+  -i: convert from ISO to Glottolog (default)
+  -g: convert from Glottolog to ISO
+  -n: don't print final newline
+  -v: verbose output
+"""
+
+import argparse
+import sys
+
+from .. import iso639_5
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Convert between ISO 639-5 codes and Glottolog codes')
+    parser.add_argument('-i', '--iso2glottolog', action='store_true', help='convert from ISO to Glottolog (default)')
+    parser.add_argument('-g', '--glottolog2iso', action='store_true', help='convert from Glottolog to ISO')
+    parser.add_argument('-n', '--no-newline', action='store_true', help="don't print final newline")
+    parser.add_argument('-v', '--verbose', action='store_true', help='verbose output')
+    parser.add_argument('codes', nargs='*', help='codes to convert')
+
+    args = parser.parse_args()
+
+    if args.verbose:
+        iso639_5.VERBOSE = 1
+
+    # Read from STDIN or take codes from command line args
+    if args.codes:
+        codes = args.codes
+    else:
+        codes = sys.stdin.read().split()
+
+    # Default to ISO to Glottolog if neither flag is set
+    if not args.glottolog2iso:
+        args.iso2glottolog = True
+
+    converted = []
+    for code in codes:
+        if args.glottolog2iso:
+            result = iso639_5.glottolog2iso(code)
+        else:
+            result = iso639_5.iso2glottolog(code)
+        converted.append(result if result else 'unknown')
+
+    print(' '.join(converted), end='')
+    if not args.no_newline:
+        print()
+
+
+if __name__ == '__main__':
+    main()

iso_langcodes/cli/langgroup.py

@@ -0,0 +1,96 @@
+#!/usr/bin/env python3
+"""
+langgroup - print language groups according to ISO639-5.
+
+Usage: langgroup [OPTIONS] LANGCODE*
+
+Options:
+  -h: help
+  -c: group children
+  -g: group languages
+  -G: group by grandparent
+  -n: don't print final newline
+  -p: print parent code of each given language code
+  -P: print parents all the way up the language tree
+  -v: verbose output
+"""
+
+import argparse
+import sys
+
+from .. import iso639_5
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Print language groups according to ISO639-5')
+    parser.add_argument('-c', '--children', action='store_true', help='group children')
+    parser.add_argument('-g', '--group', action='store_true', help='group languages')
+    parser.add_argument('-G', '--grandparent', action='store_true', help='group by grandparent')
+    parser.add_argument('-n', '--no-newline', action='store_true', help="don't print final newline")
+    parser.add_argument('-p', '--parent', action='store_true', help='print parent code of each given language code')
+    parser.add_argument('-P', '--parents', action='store_true', help='print parents all the way up the language tree')
+    parser.add_argument('-v', '--verbose', action='store_true', help='verbose output')
+    parser.add_argument('langcodes', nargs='*', help='language codes')
+
+    args = parser.parse_args()
+
+    if args.verbose:
+        iso639_5.VERBOSE = 1
+
+    # Read from STDIN or take codes from command line args
+    if args.langcodes:
+        codes = args.langcodes
+    else:
+        codes = sys.stdin.read().split()
+
+    if args.parent:
+        converted = [iso639_5.language_parent(code) for code in codes]
+        print(' '.join(str(c) for c in converted), end='')
+        if not args.no_newline:
+            print()
+    elif args.parents:
+        trees = []
+        for lang in codes:
+            parents = []
+            while True:
+                p = iso639_5.language_parent(lang)
+                if not p:
+                    break
+                parents.append(p)
+                lang = p
+                if p == 'mul':
+                    break
+            if parents:
+                trees.append(':'.join(parents))
+            else:
+                trees.append('none')
+        print(' '.join(trees), end='')
+        if not args.no_newline:
+            print()
+    elif args.group or args.grandparent:
+        groups = {}
+        for code in codes:
+            parent = iso639_5.language_parent(code) or code
+            if args.grandparent:
+                parent = iso639_5.language_parent(parent) or parent
+            if parent not in groups:
+                groups[parent] = set()
+            groups[parent].add(code)
+        for key in sorted(groups.keys()):
+            if args.no_newline:
+                print('+'.join(sorted(groups[key])), end=' ')
+            else:
+                print(key, end='\t')
+                print(' '.join(sorted(groups[key])))
+    else:
+        for code in codes:
+            if args.children:
+                print(' '.join(iso639_5.language_group_children(code)), end='')
+            else:
+                print(' '.join(iso639_5.language_group(code)), end='')
+            if not args.no_newline:
+                print()
+
+
+if __name__ == '__main__':
+    main()

iso_langcodes/cli/langscript.py

@@ -0,0 +1,135 @@
+#!/usr/bin/env python3
+"""
+langscript - detect characters from various scripts.
+
+Usage: langscript [OPTIONS] < input.txt > script-codes.txt
+
+Find the script of a text and print the script codes line by line.
+
+Options:
+  -a ............ print all scripts found in each line
+  -l <langid> ... language hint (start by looking at language-specific scripts first)
+  -L ............ two-column input (langid <TAB> text)
+  -n ............ print script names instead of script codes
+  -h ............ print usage information
+  -r ............ also print region/territory
+  -R ............ like -r but print default region if no other region found
+  -D ............ suppress default script codes
+  -1 ............ also print ISO-639-1 code
+  -3 ............ also print ISO-639-3 code
+"""
+
+import argparse
+import sys
+
+from .. import iso15924
+from .. import iso639_3
+
+
+def get_region(lang, use_default=False):
+    """Get region and cache values to avoid looking them up again."""
+    region = iso15924.language_territory(lang, use_default) or "XX"
+    return region
+
+
+def get_default_region(lang):
+    """Get default region and cache values to avoid looking them up again."""
+    region = iso15924.default_territory(lang) or "XX"
+    return region
+
+
+def get_default_script(lang):
+    """Get default script and cache values to avoid looking them up again."""
+    script = iso15924.default_script(lang) or ""
+    return script
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Detect characters from various scripts')
+    parser.add_argument('-a', '--all', action='store_true', help='print all scripts found in each line')
+    parser.add_argument('-l', '--lang', help='language hint')
+    parser.add_argument('-L', '--lang-text', action='store_true', help='two-column input (langid <TAB> text)')
+    parser.add_argument('-n', '--names', action='store_true', help='print script names instead of script codes')
+    parser.add_argument('-r', '--region', action='store_true', help='also print region/territory')
+    parser.add_argument('-R', '--region-default', action='store_true', help='like -r but print default region if no other region found')
+    parser.add_argument('-D', '--suppress-default', action='store_true', help='suppress default script codes')
+    parser.add_argument('-1', '--iso639-1', action='store_true', help='also print ISO-639-1 code')
+    parser.add_argument('-3', '--iso639-3', action='store_true', help='also print ISO-639-3 code')
+
+    args = parser.parse_args()
+
+    default_script = ""
+    default_region = "XX"
+    region = "XX"
+
+    if args.lang:
+        default_script = get_default_script(args.lang)
+        default_region = get_default_region(args.lang)
+        region = get_region(args.lang, args.region_default)
+
+    for line in sys.stdin:
+        line = line.rstrip('\n')
+        if args.lang_text:
+            parts = line.split('\t')
+            if len(parts) >= 2:
+                lang = parts[0]
+                text = parts[1]
+            else:
+                lang = args.lang
+                text = line
+        else:
+            lang = args.lang
+            text = line
+
+        if args.lang_text:
+            default_region = get_default_region(lang)
+            default_script = get_default_script(lang)
+
+        if args.all:
+            scripts = iso15924.script_of_string(text, lang, allow_non_standard=True)
+            if isinstance(scripts, dict):
+                sorted_scripts = sorted(scripts.keys(), key=lambda s: scripts[s], reverse=True)
+                for s in sorted_scripts:
+                    if args.names:
+                        print(f"{iso15924.script_name(s)} ({scripts[s]})", end=' ')
+                    else:
+                        print(f"{s} ({scripts[s]})", end=' ')
+            print()
+        else:
+            output = []
+            langcode = lang
+
+            if lang:
+                if lang == 'ku' or lang == 'kur':
+                    script = iso15924.script_of_string(text, lang)
+                    if script:
+                        langid = f'ku_{script}'
+                        default_script = get_default_script(iso639_3.get_iso639_3(langid))
+                if args.iso639_1:
+                    output.append(iso639_3.get_iso639_1(langcode, True))
+                elif args.iso639_3:
+                    output.append(iso639_3.get_iso639_3(langcode, True))
+
+            script = iso15924.script_of_string(text, lang) or default_script
+
+            if not args.suppress_default or (script != default_script and script != 'Zyyy'):
+                if args.names:
+                    if script:
+                        output.append(iso15924.script_name(script))
+                else:
+                    if script:
+                        output.append(script)
+
+            # Update region if we have dynamic language labels
+            if lang and (args.region or args.region_default):
+                if args.lang_text:
+                    region = get_region(lang, args.region_default)
+                if not args.suppress_default or (region != default_region and region != 'XX'):
+                    if region:
+                        output.append(region)
+
+            print('_'.join(output))
+
+
+if __name__ == '__main__':
+    main()

iso_langcodes/data/__init__.py

@@ -0,0 +1 @@
+"""Data package for langcodes."""