glyphsets_decomposed_chars.py

import glyphsets
from gflanguages import LoadLanguages
from fontTools import unicodedata


def get_decomposed_chars(glyphset_name, langs=None):
    if langs is None:
        langs = LoadLanguages()
    allchars = set()
    for lang_code in glyphsets.languages_per_glyphset(glyphset_name):
        lang = langs[lang_code]
        allchars.update(getattr(getattr(lang, "exemplar_chars", {}), "base", "").split(" "))
        if glyphsets.get_glyphset_definition(glyphset_name).get("use_auxiliary"):
            allchars.update(getattr(getattr(lang, "exemplar_chars", {}), "auxiliary", "").split(" "))
    decomposed_chars = sorted([
        g[1:-1] for g in allchars
        if any(unicodedata.combining(c) for c in g) and g.startswith("{") and g.endswith("}")
    ])

    return decomposed_chars


if __name__ == "__main__":
    import sys
    args = sys.argv[1:]
    if not len(args):
        print("Provide a glyphset name")
    for arg in args:
        print(arg)
        print(" ".join(get_decomposed_chars(arg)))