#!/usr/bin/env python3
from morphgnt.utils import load_yaml, load_wordset, sorted_items
lexemes = load_yaml("lexemes.yaml")
already = load_wordset("nominal-indeclinable.txt")
for lexeme, metadata in sorted_items(lexemes):
danker = metadata.get("danker-entry", "")
dodson_pos = metadata.get("dodson-pos", "")
mounce_morphcat = metadata.get("mounce-morphcat", "")
if (
lexeme in already or
dodson_pos == "N-PRI" or
mounce_morphcat == "n-3g(2)"
):
print("{:20}|{:45}|{:10}|{:10}|{:5}".format(
lexeme,
danker,
dodson_pos,
mounce_morphcat,
"yes" if lexeme in already else "no",
))
if lexeme in already:
already.remove(lexeme)
print(already)
#!/usr/bin/env python3
from morphgnt.utils import load_yaml, sorted_items
lexemes = load_yaml("lexemes.yaml")
# skip these for now until we work out how to handle them
SKIP = ["Ἀππίου", "Λιμήν", "Πάγος", "Πόλις", "Ταβέρνη", "Φόρον"]
for lexeme, metadata in sorted_items(lexemes):
if "full-citation-form" in metadata and lexeme not in SKIP:
lexeme = lexeme.split("/")[0]
citation_form = metadata["full-citation-form"]
print("{}: {}".format(lexeme, citation_form))
for alt in citation_form.split(" / "):
components = alt.split(", ")
assert len(components) <= 6
if len(components) == 1:
assert components[0] == lexeme
elif len(components) == 2:
assert components[0] == lexeme
assert components[1] in ["ὁ", "ἡ", "τό"]
elif len(components) == 3:
if components[2].startswith(("acc.", "dat.", "pl.")):
assert components[0] == lexeme
assert components[1] in ["ὁ", "ἡ", "τό", "τά"]
else:
assert components[0] == lexeme
assert components[2] in [
"ὁ", "ἡ", "τό", "ὁ/ἡ", "ὁ/τό", "οἱ", "αἱ", "τά"
]
elif mood in "DSO":
pass
elif mood in "P":
pass
elif mood in "N":
pass
else:
raise ValueError
SKIP_LIST = [
"σαβαχθάνι",
"χρή",
]
for lemma, form_dict in sorted_items(forms):
if lemma in SKIP_LIST:
continue
print()
for tense_voice in sorted(form_dict):
first_singular_forms = set()
for endings in ENDINGS[tense_voice]:
fail = False
stems = []
num = endings["num"]
first_singular = endings["1S"]
for person_number, ending in sorted(endings.items()):
if person_number == "num":
continue
ending = sorted(ending.split("/"))
gender = row["ccat-parse"][6]
case_number = row["ccat-parse"][4:6]
form_list = forms.setdefault(lemma, {}).setdefault(tense_voice_mood, {}).setdefault(gender, {}).setdefault(case_number, {}).setdefault("forms", [])
if {"form": form} not in form_list:
form_list.append({"form": form})
else:
print >>sys.stderr, "*** can't handle mood {}".format(mood)
elif lexeme["pos"] in ["P", "X"]:
form_list = forms.setdefault(lemma, {}).setdefault("forms", [])
if {"form": form} not in form_list:
form_list.append({"form": form})
else:
print >>sys.stderr, "lexemes file doesn't have {}".format(row["lemma"])
for form, metadata in sorted_items(forms):
print "{}:".format(form.encode("utf-8"))
pos = lexemes[form]["pos"]
if pos in ["RA", "A", "N", "RR"]:
for gender in ["M", "F", "N"]:
if gender in metadata:
print " {}:".format(gender)
for case_number in ["NS", "AS", "GS", "DS", "VS", "NP", "AP", "GP", "DP", "VP"]:
if case_number in metadata[gender]:
print " {}:".format(case_number)
print " forms:"
for form in metadata[gender][case_number]["forms"]:
print " -"
print " form: {}".format(form["form"].encode("utf-8"))
elif pos in ["RP1"]:
for case_number in ["NS", "AS", "GS", "DS", "VS", "NP", "AP", "GP", "DP", "VP"]:
strip_accents(row["norm"]))
elif mood in "DSO":
pass
elif mood in "P":
pass
elif mood in "N":
pass
else:
raise ValueError
SKIP_LIST = [
"σαβαχθάνι",
"χρή",
]
for lemma, form_dict in sorted_items(forms):
if lemma in SKIP_LIST:
continue
print()
for tense_voice in sorted(form_dict):
first_singular_forms = set()
for endings in ENDINGS[tense_voice]:
fail = False
stems = []
num = endings["num"]
first_singular = endings["1S"]
for person_number, ending in sorted(endings.items()):
if person_number == "num":
continue
ending = sorted(ending.split("/"))
# syncretism
if parse[2] == "N":
if parse[0] == "N":
forms[norm].add("A" + parse[1:])
if parse[0] == "A":
forms[norm].add("N" + parse[1:])
if "n-1a" in mounce:
if parse == "APF":
forms[norm].add("GSF")
if parse == "GSF":
forms[norm].add("APF")
if "n-1d" in mounce:
if parse == "NSM":
forms[norm].add("APM")
if parse == "APM":
forms[norm].add("NSM")
if "n-3e(3)" in mounce or "n-3e(5b)" in mounce:
if parse[:2] == "AP":
forms[norm].add("NP" + parse[2])
if parse[:2] == "NP":
forms[norm].add("AP" + parse[2])
for form, data in sorted_items(forms):
if cats[form]:
cat_string = ":".join(cats[form])
else:
cat_string = "@@@"
print("{}|{}|{}|{}".format(form, cat_string, ":".join(sorted(data)),
counts[form]))
if parse[2] == "N":
if parse[0] == "N":
forms[norm].add("A" + parse[1:])
if parse[0] == "A":
forms[norm].add("N" + parse[1:])
if "n-1a" in mounce:
if parse == "APF":
forms[norm].add("GSF")
if parse == "GSF":
forms[norm].add("APF")
if "n-1d" in mounce:
if parse == "NSM":
forms[norm].add("APM")
if parse == "APM":
forms[norm].add("NSM")
if "n-3e(3)" in mounce or "n-3e(5b)" in mounce:
if parse[:2] == "AP":
forms[norm].add("NP" + parse[2])
if parse[:2] == "NP":
forms[norm].add("AP" + parse[2])
for form, data in sorted_items(forms):
if cats[form]:
cat_string = ":".join(cats[form])
else:
cat_string = "@@@"
print("{}|{}|{}|{}".format(
form, cat_string, ":".join(sorted(data)), counts[form]))
#!/usr/bin/env python
# coding: utf-8
import sys
from morphgnt.utils import load_yaml, sorted_items
danker = load_yaml("../data-cleanup/danker-concise-lexicon/components.yaml")
derivation = load_yaml("derivation.yaml")
skipped = 0
existing = 0
added = 0
for lexeme, metadata in sorted_items(danker):
components = metadata["components"].strip()
print "{}:".format(lexeme.encode("utf-8"))
if lexeme in derivation:
if derivation[lexeme]:
def q(key):
if key in derivation[lexeme]:
if isinstance(derivation[lexeme][key], list):
print " {}:".format(key)
for item in derivation[lexeme][key]:
print " - {}".format(item.encode("utf-8"))
else:
print " {}: {}".format(
key, derivation[lexeme][key].encode("utf-8"))
#!/usr/bin/env python
# coding: utf-8
import sys
from morphgnt.utils import load_yaml, sorted_items
danker = load_yaml("../data-cleanup/danker-concise-lexicon/components.yaml")
derivation = load_yaml("derivation.yaml")
skipped = 0
existing = 0
added = 0
for lexeme, metadata in sorted_items(danker):
components = metadata["components"].strip()
print "{}:".format(lexeme.encode("utf-8"))
if lexeme in derivation:
if derivation[lexeme]:
def q(key):
if key in derivation[lexeme]:
if isinstance(derivation[lexeme][key], list):
print " {}:".format(key)
for item in derivation[lexeme][key]:
print " - {}".format(item.encode("utf-8"))
else:
print " {}: {}".format(key, derivation[lexeme][key].encode("utf-8"))
q("derivation")