Reordeno ejemplos en json en una carpeta "examples" aparte, con el no…

…mbre que tendrían en la realidad. Dejo sólo la lista de themes del superThemeTaxonomy, sin la key superThemeTaxonomy (la definición de la taxonomía es independiente del nombre de la variable).

.gitignore

@@ -0,0 +1 @@
+.ipynb_checkpoints

Generación de ejemplos.ipynb

@@ -0,0 +1,309 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Generación de ejemplos"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Genero ejemplos de metadatos a partir del ejemplo de `data.json`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "from pprint import pprint"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "with open(\"data.json\", \"rb\") as f:\n",
+    "    data = json.load(f)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Exploración del data.json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "13\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[u'rights',\n",
+       " u'publisher',\n",
+       " u'license',\n",
+       " u'description',\n",
+       " u'language',\n",
+       " u'title',\n",
+       " u'issued',\n",
+       " u'superThemeTaxonomy',\n",
+       " u'modified',\n",
+       " u'themeTaxonomy',\n",
+       " u'spatial',\n",
+       " u'dataset',\n",
+       " u'homepage']"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# campos de metadata de un catalog\n",
+    "print len(data)\n",
+    "data.keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "17\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[u'publisher',\n",
+       " u'landingPage',\n",
+       " u'description',\n",
+       " u'superTheme',\n",
+       " u'title',\n",
+       " u'issued',\n",
+       " u'temporal',\n",
+       " u'modified',\n",
+       " u'language',\n",
+       " u'theme',\n",
+       " u'keyword',\n",
+       " u'accrualPeriodicity',\n",
+       " u'spatial',\n",
+       " u'license',\n",
+       " u'contactPoint',\n",
+       " u'identifier',\n",
+       " u'distribution']"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# campos de metadata de un dataset\n",
+    "print len(data[\"dataset\"][0].keys())\n",
+    "data[\"dataset\"][0].keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "12\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[u'accessURL',\n",
+       " u'rights',\n",
+       " u'description',\n",
+       " u'license',\n",
+       " u'title',\n",
+       " u'byteSize',\n",
+       " u'format',\n",
+       " u'mediaType',\n",
+       " u'modified',\n",
+       " u'downloadURL',\n",
+       " u'field',\n",
+       " u'issued']"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# campos de metadata de un distribucion\n",
+    "print len(data[\"dataset\"][0][\"distribution\"][0].keys())\n",
+    "data[\"dataset\"][0][\"distribution\"][0].keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "3\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[u'type', u'description', u'title']"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# campos de metadata de un field\n",
+    "print len(data[\"dataset\"][0][\"distribution\"][0][\"field\"][0].keys())\n",
+    "data[\"dataset\"][0][\"distribution\"][0][\"field\"][0].keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "3\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[u'description', u'id', u'label']"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# campos de metadata de un theme\n",
+    "print len(data[\"themeTaxonomy\"][0].keys())\n",
+    "data[\"themeTaxonomy\"][0].keys()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Separación de ejemplos en JSON"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "def write_to_json(example_name, example):\n",
+    "    with open(\"examples/{}.json\".format(example_name), \"wb\") as f:\n",
+    "        f.write(json.dumps(example, f, indent=4, ensure_ascii=False).encode(\"utf8\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "write_to_json(\"dataset\", data[\"dataset\"][0])\n",
+    "write_to_json(\"distribution\", data[\"dataset\"][0][\"distribution\"][0])\n",
+    "write_to_json(\"field\", data[\"dataset\"][0][\"distribution\"][0][\"field\"][0])\n",
+    "write_to_json(\"theme\", data[\"themeTaxonomy\"][0])\n",
+    "write_to_json(\"themeTaxonomy\", data[\"themeTaxonomy\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "anaconda-cloud": {},
+  "kernelspec": {
+   "display_name": "Python [Root]",
+   "language": "python",
+   "name": "Python [Root]"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

ejemplo-completo.json → examples/data.json

@@ -105,7 +105,7 @@
             {
               "title": "organismo_unidad_operativa_contrataciones_id",
               "type": "integer",
-              "description": "Identificador único del organismo que realiza la convocatoría. Organismo de máximo nivel jerárquico al que pertenece la unidad operativa de contrataciones."
+              "description": "Identificador único del organismo que realiza la convocatoria. Organismo de máximo nivel jerárquico al que pertenece la unidad operativa de contrataciones."
             },
             {
               "title": "unidad_operativa_contrataciones_id",
@@ -115,7 +115,7 @@
             {
               "title": "organismo_unidad_operativa_contrataciones_desc",
               "type": "string",
-              "description": "Organismo que realiza la convocatoría. Organismo de máximo nivel jerárquico al que pertenece la unidad operativa de contrataciones."
+              "description": "Organismo que realiza la convocatoria. Organismo de máximo nivel jerárquico al que pertenece la unidad operativa de contrataciones."
             },
             {
               "title": "unidad_operativa_contrataciones_desc",