{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"
\n",
" \n",
" A | \n",
" B | \n",
"
\n",
" \n",
" the | \n",
" the | \n",
"
\n",
" \n",
" black | \n",
" black | \n",
"
\n",
" \n",
" dog | \n",
" dingo | \n",
"
\n",
"
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from collatex import *\n",
"\n",
"json_input = {\n",
" \"witnesses\" : [ \n",
" {\n",
" \"id\": \"A\",\n",
" \"tokens\": [ \n",
" { \"t\" : \"the\" }, \n",
" { \"t\" : \"black\" }, \n",
" { \"t\" : \"dog\" } \n",
" ]\n",
" },\n",
" {\n",
" \"id\": \"B\",\n",
" \"tokens\": [ \n",
" { \"t\" : \"the\" }, \n",
" { \"t\" : \"black\", \"tag\" : \"emph\" }, \n",
" { \"t\" : \"dingo\" } \n",
" ]\n",
" } \n",
" ]\n",
"}\n",
"\n",
"collate_pretokenized_json(json_input, output=\"html2\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" A | \n",
" B | \n",
"
\n",
" \n",
" the | \n",
" the | \n",
"
\n",
" \n",
" black | \n",
" black | \n",
"
\n",
" \n",
" dog | \n",
" dingo | \n",
"
\n",
"
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"def match_properties(token1_data, token2_data):\n",
" return token1_data == token2_data\n",
"\n",
"collate_pretokenized_json(json_input, properties_filter=match_properties, output=\"html2\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.4.3"
}
},
"nbformat": 4,
"nbformat_minor": 0
}