def save_triples_to_file(triples, path): try: sorted_triples = utils.sorted_items(triples) lines = [ '%s\t%s\t%s\n' % (sec, xy[0], xy[1]) for sec, xy in sorted_triples ] utils.filer.write_lines(path, lines) except: raise
verses = parse_verse_ranges(args.verses) if args.exclude: exclusions = load_wordset(args.exclude) else: exclusions = set() lexemes = load_yaml(args.lexemes) if args.headwords: headwords = load_yaml(args.headwords) else: headwords = {} for entry in get_morphgnt(verses, args.sblgnt_dir): if entry[0] == "WORD": lexeme = entry[8] if lexeme not in exclusions and lexeme not in headwords: pos = entry[2] if pos in ["N-", "A-"]: if "full-citation-form" in lexemes[lexeme]: headword = lexemes[lexeme]["full-citation-form"] else: headword = lexemes[lexeme]["danker-entry"] headwords[lexeme] = headword for lexeme, headword in sorted_items(headwords): print("{}: {}".format(lexeme, headword))
help="path to lexemes file " "(defaults to lexemes.yaml)") args = argparser.parse_args() verses = parse_verse_ranges(args.verses) if args.exclude: exclusions = load_wordset(args.exclude) else: exclusions = set() lexemes = load_yaml(args.lexemes) if args.headwords: headwords = load_yaml(args.headwords) else: headwords = {} for entry in get_morphgnt(verses): if entry[0] == "WORD": lemma = entry[1]["lemma"] if lemma not in exclusions and lemma not in headwords: pos = entry[1]["ccat-pos"] if pos in ["N-", "A-"]: headwords[lemma] = lexemes[lemma]["headword"] for lemma, headword in sorted_items(headwords): print("{}: {}".format(lemma, headword))
help="path to morphological-lexicon lexemes.yaml file " "(defaults to ../morphological-lexicon/lexemes.yaml)") args = argparser.parse_args() verses = parse_verse_ranges(args.verses) if args.exclude: exclusions = load_wordset(args.exclude) else: exclusions = set() lexemes = load_yaml(args.lexemes) if args.glosses: glosses = load_yaml(args.glosses) else: glosses = {} for entry in get_morphgnt(verses): if entry[0] == "WORD": lemma = entry[1]["lemma"] if lemma not in exclusions and lemma not in glosses: glosses[lemma] = {"default": lexemes[lemma].get("gloss", "\"@@@\"")} for lemma, gloss_entries in sorted_items(glosses): print("{}:".format(lemma)) for k, v in sorted_items(gloss_entries): print(" {}: {}".format(k, v))
#!/usr/bin/env python3 """ Note that this is a one-off script to pull in the lexemes.yaml data from morphological-lexicon and store it here. Once the reduced lexemes.yaml is in this repo, this script exists only for historical interest and reproducibility. """ from utils import load_yaml, sorted_items for key, value in sorted_items( load_yaml("../../morphgnt/morphological-lexicon/lexemes.yaml")): print("{}:".format(key)) headword = value.get("full-citation-form", value.get("danker-entry", key)) gloss = value.get("gloss") print(" headword: {}".format(headword)) if gloss: print(" gloss: {}".format(gloss))
"(defaults to lexemes.yaml)") args = argparser.parse_args() verses = parse_verse_ranges(args.verses) if args.exclude: exclusions = load_wordset(args.exclude) else: exclusions = set() lexemes = load_yaml(args.lexemes) if args.glosses: glosses = load_yaml(args.glosses) else: glosses = {} for entry in get_morphgnt(verses): if entry[0] == "WORD": lemma = entry[1]["lemma"] if lemma not in exclusions and lemma not in glosses: glosses[lemma] = { "default": lexemes[lemma].get("gloss", "\"@@@\"") } for lemma, gloss_entries in sorted_items(glosses): print("{}:".format(lemma)) for k, v in sorted_items(gloss_entries): print(" {}: {}".format(k, v))
dest="sblgnt_dir", default="../sblgnt", help="path to MorphGNT sblgnt directory (defaults to ../sblgnt)") args = argparser.parse_args() verses = parse_verse_ranges(args.verses) if args.exclude: exclusions = load_wordset(args.exclude) else: exclusions = set() lexemes = load_yaml(args.lexemes) if args.glosses: glosses = load_yaml(args.glosses) else: glosses = {} for entry in get_morphgnt(verses, args.sblgnt_dir): if entry[0] == "WORD": lexeme = entry[8] if lexeme not in exclusions and lexeme not in glosses: glosses[lexeme] = {"default": lexemes[lexeme].get("gloss", "@@@")} for lexeme, gloss_entries in sorted_items(glosses): print("{}:".format(lexeme)) for k, v in sorted_items(gloss_entries): print(" {}: {}".format(k, v))
#!/usr/bin/env python3 """ Note that this is a one-off script to pull in the lexemes.yaml data from morphological-lexicon and store it here. Once the reduced lexemes.yaml is in this repo, this script exists only for historical interest and reproducibility. """ from utils import load_yaml, sorted_items for key, value in sorted_items(load_yaml("../../morphgnt/morphological-lexicon/lexemes.yaml")): print("{}:".format(key)) headword = value.get("full-citation-form", value.get("danker-entry", key)) gloss = value.get("gloss") print(" headword: {}".format(headword)) if gloss: print(" gloss: {}".format(gloss))