{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "7f9e8728", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import stanza\n", "import numpy as np\n", "from stanza.models.common.doc import Word" ] }, { "cell_type": "code", "execution_count": 2, "id": "302ae754", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2022-05-27 22:12:51 INFO: Loading these models for language: hu (Hungarian):\n", "=======================\n", "| Processor | Package |\n", "-----------------------\n", "| tokenize | szeged |\n", "| pos | szeged |\n", "| lemma | szeged |\n", "| depparse | szeged |\n", "=======================\n", "\n", "2022-05-27 22:12:51 INFO: Use device: cpu\n", "2022-05-27 22:12:51 INFO: Loading: tokenize\n", "2022-05-27 22:12:52 INFO: Loading: pos\n", "2022-05-27 22:12:52 INFO: Loading: lemma\n", "2022-05-27 22:12:52 INFO: Loading: depparse\n", "2022-05-27 22:12:52 INFO: Done loading processors!\n" ] } ], "source": [ "nlp=stanza.Pipeline(\"hu\",processors='tokenize,pos,lemma,depparse')" ] }, { "cell_type": "code", "execution_count": 7, "id": "4d8d3739", "metadata": {}, "outputs": [], "source": [ "text=\"Mi nem vagyunk magyarok.\"\n", "text=\"− Én sem értem, hogy miért keresek ma mindent.\"\n", "text=\"Koridor itu beraroma kubis rebus dan karpet butut.\"\n", "text=\"Pada mulanya, waktu Allah mulai menciptakan alam semesta\"\n", "text='dan dinamakan-Nya terang itu \"Siang\" dan gelap itu \"Malam\"'\n", "text=\"Koridor itu beraroma kubisnya rebus dan karpet butut.\"\n", "text=\"Apakah Allah benar-benar, melarang :e: terbesar terjelas kalian-nya makan buah-buahan dari segala pohon di taman ini?\"\n", "text=\"WAKTU itu musim semi tahun 1894. Seluruh dikenal dilakukan penduduk kota London gempar atas terbunuhnya\"\n", "text=\"A nagyon szép nőhöz megyem. kitörésröl kitörésekre Amerikából\"\n", "text= \"Kazahsztánban a mai kazak nyelv cirill betűs írást használ.\"# Közeli rokonai a kirgiz, a tatár, a baskír, valamint a kihalt besenyő és kun nyelvek.\"" ] }, { "cell_type": "code", "execution_count": null, "id": "e34d01e4", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 8, "id": "4eb2a3dc", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
idtextlemmauposfeatsheaddeprelstart_charend_char
01KazahsztánbanKazahsztánPROPNCase=Ine|Number=Sing9obl013
02aaDETDefinite=Def|PronType=Art5det1415
03maimaiADJCase=Nom|Degree=Pos|Number=Sing5amod:att1619
04kazakkazakADJCase=Nom|Degree=Pos|Number=Sing5amod:att2025
05nyelvnyelvNOUNCase=Nom|Number=Sing9nsubj2631
06cirillcirillADJCase=Nom|Degree=Pos|Number=Sing8amod:att3238
07betűsbetűsADJCase=Nom|Degree=Pos|Number=Sing8amod:att3944
08írástírásNOUNCase=Acc|Number=Sing9obj4550
09használhasználVERBDefinite=Ind|Mood=Ind|Number=Sing|Person=3|Ten...0root5158
010..PUNCTNaN9punct5859
\n", "
" ], "text/plain": [ " id text lemma upos \\\n", "0 1 Kazahsztánban Kazahsztán PROPN \n", "0 2 a a DET \n", "0 3 mai mai ADJ \n", "0 4 kazak kazak ADJ \n", "0 5 nyelv nyelv NOUN \n", "0 6 cirill cirill ADJ \n", "0 7 betűs betűs ADJ \n", "0 8 írást írás NOUN \n", "0 9 használ használ VERB \n", "0 10 . . PUNCT \n", "\n", " feats head deprel \\\n", "0 Case=Ine|Number=Sing 9 obl \n", "0 Definite=Def|PronType=Art 5 det \n", "0 Case=Nom|Degree=Pos|Number=Sing 5 amod:att \n", "0 Case=Nom|Degree=Pos|Number=Sing 5 amod:att \n", "0 Case=Nom|Number=Sing 9 nsubj \n", "0 Case=Nom|Degree=Pos|Number=Sing 8 amod:att \n", "0 Case=Nom|Degree=Pos|Number=Sing 8 amod:att \n", "0 Case=Acc|Number=Sing 9 obj \n", "0 Definite=Ind|Mood=Ind|Number=Sing|Person=3|Ten... 0 root \n", "0 NaN 9 punct \n", "\n", " start_char end_char \n", "0 0 13 \n", "0 14 15 \n", "0 16 19 \n", "0 20 25 \n", "0 26 31 \n", "0 32 38 \n", "0 39 44 \n", "0 45 50 \n", "0 51 58 \n", "0 58 59 " ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "doc = nlp(text) \n", "wordlist=pd.concat([pd.Series(word.to_dict()).to_frame().T for sentence in doc.sentences for word in sentence.words])\n", "wordlist" ] }, { "cell_type": "code", "execution_count": 5, "id": "a9e0c2b2", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Definite=Ind|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act'" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "wordlist.iloc[4][\"feats\"]" ] }, { "cell_type": "code", "execution_count": 21, "id": "8468fa0b", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/maxwell/.local/lib/python3.8/site-packages/pandas/core/series.py:1056: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " cacher_needs_updating = self._check_is_chained_assignment_possible()\n" ] }, { "ename": "IndexError", "evalue": "string index out of range", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mIndexError\u001b[0m Traceback (most recent call last)", "Input \u001b[0;32mIn [21]\u001b[0m, in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 20\u001b[0m wordlist\u001b[38;5;241m.\u001b[39miloc[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mend_char_prev\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0\u001b[39m\n\u001b[1;32m 21\u001b[0m wordlist[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mseparator_prev\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m=\u001b[39mwordlist[[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mend_char_prev\u001b[39m\u001b[38;5;124m\"\u001b[39m,\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstart_char\u001b[39m\u001b[38;5;124m\"\u001b[39m]]\u001b[38;5;241m.\u001b[39mapply(\u001b[38;5;28;01mlambda\u001b[39;00m x: text[x[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mend_char_prev\u001b[39m\u001b[38;5;124m\"\u001b[39m]:x[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstart_char\u001b[39m\u001b[38;5;124m\"\u001b[39m]], axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m---> 23\u001b[0m sep_end\u001b[38;5;241m=\u001b[39m\u001b[43mtext\u001b[49m\u001b[43m[\u001b[49m\u001b[43mwordlist\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43miloc\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mend_char\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m 24\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(\u001b[38;5;28mlist\u001b[39m(wordlist[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mseparator_prev\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m+\u001b[39mwordlist[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtranslemma\u001b[39m\u001b[38;5;124m\"\u001b[39m])\u001b[38;5;241m+\u001b[39m[sep_end]))\n", "\u001b[0;31mIndexError\u001b[0m: string index out of range" ] } ], "source": [ "folder=\"~/Desktop/Regina Phalange/Conlang/\"\n", "dic=pd.read_csv(folder+\"dict.csv\",sep=\";\")\n", "lemmadict=dict(zip(dic[\"lemma\"],dic[\"translation\"]))\n", "capitalize_get = lambda x : x[\"text\"][0].isupper()\n", "wordlist[\"capitalize\"] = wordlist[[\"text\"]].apply(capitalize_get, axis=1)\n", "capitalize_apply = lambda x,y : x[0].upper()+x[1:] if y else x\n", "def lemmadictget (x):\n", " if x[\"upos\"]!=\"PUNCT\":\n", " if x[\"lemma\"] in lemmadict.keys():\n", " return capitalize_apply(lemmadict[x[\"lemma\"]], x[\"capitalize\"])\n", " else:\n", " return \"*\"+capitalize_apply(x[\"lemma\"], x[\"capitalize\"])\n", " else:\n", " return x[\"text\"]\n", "\n", "wordlist[\"translemma\"] = wordlist[[\"lemma\",\"upos\",\"text\",\"capitalize\"]].apply(lemmadictget, axis=1)\n", "\n", "\n", "wordlist['end_char_prev'] = np.roll(wordlist['end_char'],1)\n", "wordlist.iloc[0]['end_char_prev']=0\n", "wordlist[\"separator_prev\"]=wordlist[[\"end_char_prev\",\"start_char\"]].apply(lambda x: text[x[\"end_char_prev\"]:x[\"start_char\"]], axis=1)\n", "\n", "sep_end=text[wordlist.iloc[-1][\"end_char\"]]\n", "print(\"\".join(list(wordlist[\"separator_prev\"]+wordlist[\"translemma\"])+[sep_end]))" ] }, { "cell_type": "code", "execution_count": null, "id": "3640f3d7", "metadata": {}, "outputs": [], "source": [ "\n", "\n", "# depict\n", "pd.set_option(\"display.max_rows\", None, \"display.max_columns\", None)\n", "print(wordlist)\n", "import networkx as nx\n", "import graphviz\n", "w = graphviz.Digraph()\n", "for i,row in wordlist.iterrows(): w.node(str(row[\"id\"]), \"\\n\".join(row[:-2].apply(str)))\n", "\n", "for i,row in wordlist.iterrows(): w.edge(str(row[\"id\"]), str(row[\"head\"]))\n", "\n", "w.render('test-output/round-table.gv', view=True)\n", "\n", "folder=\"~/Desktop/Regina Phalange/Conlang/\"\n", "dic=pd.read_csv(folder+\"dict.csv\",sep=\";\")\n", "lemmadict=dict(zip(dic[\"lemma\"],dic[\"translation\"]))\n", "capitalize_get = lambda x : x[\"text\"][0].isupper()\n", "wordlist[\"capitalize\"] = wordlist[[\"text\"]].apply(capitalize_get, axis=1)\n", "capitalize_apply = lambda x,y : x[0].upper()+x[1:] if y else x\n", "def lemmadictget (x):\n", " if x[\"upos\"]!=\"PUNCT\":\n", " if x[\"lemma\"] in lemmadict.keys():\n", " return capitalize_apply(lemmadict[x[\"lemma\"]], x[\"capitalize\"])\n", " else:\n", " return \"*\"+capitalize_apply(x[\"lemma\"], x[\"capitalize\"])\n", " else:\n", " return x[\"text\"]\n", "\n", "wordlist[\"translemma\"] = wordlist[[\"lemma\",\"upos\",\"text\",\"capitalize\"]].apply(lemmadictget, axis=1)\n", "\n", "\n", "wordlist['end_char_prev'] = np.roll(wordlist['end_char'],1)\n", "wordlist.iloc[0]['end_char_prev']=0\n", "wordlist[\"separator_prev\"]=wordlist[[\"end_char_prev\",\"start_char\"]].apply(lambda x: text[x[\"end_char_prev\"]:x[\"start_char\"]], axis=1)\n", "\n", "sep_end=text[wordlist.iloc[-1][\"end_char\"]]\n", "print(\"\".join(list(wordlist[\"separator_prev\"]+wordlist[\"translemma\"])+[sep_end]))" ] }, { "cell_type": "code", "execution_count": 43, "id": "dbdf7be0", "metadata": {}, "outputs": [], "source": [ "import unimorph as um" ] }, { "cell_type": "code", "execution_count": 46, "id": "7a0de9a6", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Cloning into 'ru'...\n", "fatal: could not read Username for 'https://github.com': No such device or address\n" ] }, { "ename": "CalledProcessError", "evalue": "Command '['git', 'clone', 'https://github.com/unimorph/ru.git']' returned non-zero exit status 128.", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mCalledProcessError\u001b[0m Traceback (most recent call last)", "Input \u001b[0;32mIn [46]\u001b[0m, in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mum\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdownload_unimorph\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlang\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mru\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.local/lib/python3.8/site-packages/unimorph.py:67\u001b[0m, in \u001b[0;36mdownload_unimorph\u001b[0;34m(lang)\u001b[0m\n\u001b[1;32m 65\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m not_loaded(lang):\n\u001b[1;32m 66\u001b[0m logging\u001b[38;5;241m.\u001b[39minfo(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDownloading unimorph/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mlang\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m to \u001b[39m\u001b[38;5;132;01m{\u001b[39;00moutput_dir\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 67\u001b[0m \u001b[43msubprocess\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 68\u001b[0m \u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mgit\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mclone\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mhttps://github.com/unimorph/\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mlang\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m.git\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 69\u001b[0m \u001b[43m \u001b[49m\u001b[43mcheck\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 70\u001b[0m \u001b[43m \u001b[49m\u001b[43mcwd\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mUNIMORPH_DIR\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 71\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m output_dir\u001b[38;5;241m.\u001b[39mis_dir()\n", "File \u001b[0;32m/usr/lib/python3.8/subprocess.py:516\u001b[0m, in \u001b[0;36mrun\u001b[0;34m(input, capture_output, timeout, check, *popenargs, **kwargs)\u001b[0m\n\u001b[1;32m 514\u001b[0m retcode \u001b[38;5;241m=\u001b[39m process\u001b[38;5;241m.\u001b[39mpoll()\n\u001b[1;32m 515\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check \u001b[38;5;129;01mand\u001b[39;00m retcode:\n\u001b[0;32m--> 516\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m CalledProcessError(retcode, process\u001b[38;5;241m.\u001b[39margs,\n\u001b[1;32m 517\u001b[0m output\u001b[38;5;241m=\u001b[39mstdout, stderr\u001b[38;5;241m=\u001b[39mstderr)\n\u001b[1;32m 518\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m CompletedProcess(process\u001b[38;5;241m.\u001b[39margs, retcode, stdout, stderr)\n", "\u001b[0;31mCalledProcessError\u001b[0m: Command '['git', 'clone', 'https://github.com/unimorph/ru.git']' returned non-zero exit status 128." ] } ], "source": [ "um.download_unimorph(lang=\"ru\")" ] }, { "cell_type": "code", "execution_count": 45, "id": "e216aa12", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Cloning into 'ru'...\n", "fatal: could not read Username for 'https://github.com': No such device or address\n" ] }, { "ename": "CalledProcessError", "evalue": "Command '['git', 'clone', 'https://github.com/unimorph/ru.git']' returned non-zero exit status 128.", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mCalledProcessError\u001b[0m Traceback (most recent call last)", "Input \u001b[0;32mIn [45]\u001b[0m, in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mum\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43manalyze_word\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mсвистишь\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlang\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mru\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/.local/lib/python3.8/site-packages/unimorph.py:113\u001b[0m, in \u001b[0;36manalyze_word\u001b[0;34m(word, lang)\u001b[0m\n\u001b[1;32m 112\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21manalyze_word\u001b[39m(word: \u001b[38;5;28mstr\u001b[39m, \u001b[38;5;241m*\u001b[39m, lang: \u001b[38;5;28mstr\u001b[39m):\n\u001b[0;32m--> 113\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[43mload_dataset\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlang\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m data[data\u001b[38;5;241m.\u001b[39mform \u001b[38;5;241m==\u001b[39m word]\u001b[38;5;241m.\u001b[39mto_csv(sep\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\t\u001b[39;00m\u001b[38;5;124m\"\u001b[39m, index\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, header\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m)\n", "File \u001b[0;32m~/.local/lib/python3.8/site-packages/unimorph.py:79\u001b[0m, in \u001b[0;36mload_dataset\u001b[0;34m(lang, specific_file)\u001b[0m\n\u001b[1;32m 76\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m specific_file \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 77\u001b[0m specific_file \u001b[38;5;241m=\u001b[39m lang\n\u001b[0;32m---> 79\u001b[0m \u001b[43mdownload_unimorph\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlang\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 81\u001b[0m language_path \u001b[38;5;241m=\u001b[39m UNIMORPH_DIR \u001b[38;5;241m/\u001b[39m lang \u001b[38;5;241m/\u001b[39m specific_file\n\u001b[1;32m 82\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m lang \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfin\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n", "File \u001b[0;32m~/.local/lib/python3.8/site-packages/unimorph.py:67\u001b[0m, in \u001b[0;36mdownload_unimorph\u001b[0;34m(lang)\u001b[0m\n\u001b[1;32m 65\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m not_loaded(lang):\n\u001b[1;32m 66\u001b[0m logging\u001b[38;5;241m.\u001b[39minfo(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDownloading unimorph/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mlang\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m to \u001b[39m\u001b[38;5;132;01m{\u001b[39;00moutput_dir\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 67\u001b[0m \u001b[43msubprocess\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 68\u001b[0m \u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mgit\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mclone\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mhttps://github.com/unimorph/\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mlang\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m.git\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 69\u001b[0m \u001b[43m \u001b[49m\u001b[43mcheck\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 70\u001b[0m \u001b[43m \u001b[49m\u001b[43mcwd\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mUNIMORPH_DIR\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 71\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m output_dir\u001b[38;5;241m.\u001b[39mis_dir()\n", "File \u001b[0;32m/usr/lib/python3.8/subprocess.py:516\u001b[0m, in \u001b[0;36mrun\u001b[0;34m(input, capture_output, timeout, check, *popenargs, **kwargs)\u001b[0m\n\u001b[1;32m 514\u001b[0m retcode \u001b[38;5;241m=\u001b[39m process\u001b[38;5;241m.\u001b[39mpoll()\n\u001b[1;32m 515\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check \u001b[38;5;129;01mand\u001b[39;00m retcode:\n\u001b[0;32m--> 516\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m CalledProcessError(retcode, process\u001b[38;5;241m.\u001b[39margs,\n\u001b[1;32m 517\u001b[0m output\u001b[38;5;241m=\u001b[39mstdout, stderr\u001b[38;5;241m=\u001b[39mstderr)\n\u001b[1;32m 518\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m CompletedProcess(process\u001b[38;5;241m.\u001b[39margs, retcode, stdout, stderr)\n", "\u001b[0;31mCalledProcessError\u001b[0m: Command '['git', 'clone', 'https://github.com/unimorph/ru.git']' returned non-zero exit status 128." ] } ], "source": [ "um.analyze_word(\"свистишь\", lang=\"ru\")" ] }, { "cell_type": "code", "execution_count": null, "id": "42b06aaf", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.10" } }, "nbformat": 4, "nbformat_minor": 5 }