Skip to content

gargantext
gargantext
Commit 281d7703 authored by Administrator's avatar Administrator
Browse files
Options

test for parser

parent 204cf966
Hide whitespace changes
Inline Side-by-side
Showing with 290 additions and 50 deletions
.ipynb_checkpoints/Untitled0-checkpoint.ipynb
View file @ 281d7703
{
"metadata": {
"name": "",
"signature": "sha256:490e1bc5ac44087c1b3f82ca74e40f42f49bd3910f79a088af19c708d73c63e0"
"signature": "sha256:a5146fbde2b6bf2e3ed4e2bdddfb62662f99272f26e82bf86110680ff3595332"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": []
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"from node.models import Node, NodeType, Language\n",
"import parsing\n",
"from parsing.FileParsers import *"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"node = Node.objects.get(name=\"PubMed corpus\")"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"fileparser = PubmedFileParser.PubmedFileParser(file='/var/www/gargantext/media/' + node.fichier.name)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"fileparser.parse(node)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"ename": "ValueError",
"evalue": "Cannot assign \"24\": \"Node.user\" must be a \"User\" instance.",
"output_type": "pyerr",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-4-8c1443001599>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mfileparser\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mparse\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnode\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32m/srv/gargantext/parsing/FileParsers/PubmedFileParser.py\u001b[0m in \u001b[0;36mparse\u001b[1;34m(self, parentNode, tag)\u001b[0m\n\u001b[0;32m 45\u001b[0m \u001b[0mlanguage\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_languages_iso3\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mmetadata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"language_iso3\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlower\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 46\u001b[0m \u001b[0mmetadata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 47\u001b[1;33m \u001b[0mguid\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"doi\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 48\u001b[0m )\n\u001b[0;32m 49\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mdocument\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/srv/gargantext/parsing/FileParsers/FileParser.py\u001b[0m in \u001b[0;36mcreate_document\u001b[1;34m(self, parentNode, title, contents, language, metadata, guid)\u001b[0m\n\u001b[0;32m 100\u001b[0m \u001b[0mmetadata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 101\u001b[0m \u001b[1;31m#resource = resource,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 102\u001b[1;33m \u001b[0mparent\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mparentNode\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 103\u001b[0m )\n\u001b[0;32m 104\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/alexandre/projets/gargantext.py/env/lib/python3.4/site-packages/django/db/models/base.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 403\u001b[0m \u001b[1;31m# \"user_id\") so that the object gets properly cached (and type\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 404\u001b[0m \u001b[1;31m# checked) by the RelatedObjectDescriptor.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 405\u001b[1;33m \u001b[0msetattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfield\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrel_obj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 406\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 407\u001b[0m \u001b[0msetattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfield\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mattname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mval\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/alexandre/projets/gargantext.py/env/lib/python3.4/site-packages/django/db/models/fields/related.py\u001b[0m in \u001b[0;36m__set__\u001b[1;34m(self, instance, value)\u001b[0m\n\u001b[0;32m 337\u001b[0m raise ValueError('Cannot assign \"%r\": \"%s.%s\" must be a \"%s\" instance.' %\n\u001b[0;32m 338\u001b[0m (value, instance._meta.object_name,\n\u001b[1;32m--> 339\u001b[1;33m self.field.name, self.field.rel.to._meta.object_name))\n\u001b[0m\u001b[0;32m 340\u001b[0m \u001b[1;32melif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 341\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0minstance\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_state\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdb\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mValueError\u001b[0m: Cannot assign \"24\": \"Node.user\" must be a \"User\" instance."
]
}
],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"node.children.all()"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
\ No newline at end of file
Untitled0.ipynb 0 → 100644
View file @ 281d7703
{
"metadata": {
"name": "",
"signature": "sha256:a5146fbde2b6bf2e3ed4e2bdddfb62662f99272f26e82bf86110680ff3595332"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"from node.models import Node, NodeType, Language\n",
"import parsing\n",
"from parsing.FileParsers import *"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"node = Node.objects.get(name=\"PubMed corpus\")"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"fileparser = PubmedFileParser.PubmedFileParser(file='/var/www/gargantext/media/' + node.fichier.name)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"fileparser.parse(node)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"ename": "ValueError",
"evalue": "Cannot assign \"24\": \"Node.user\" must be a \"User\" instance.",
"output_type": "pyerr",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-4-8c1443001599>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mfileparser\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mparse\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnode\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32m/srv/gargantext/parsing/FileParsers/PubmedFileParser.py\u001b[0m in \u001b[0;36mparse\u001b[1;34m(self, parentNode, tag)\u001b[0m\n\u001b[0;32m 45\u001b[0m \u001b[0mlanguage\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_languages_iso3\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mmetadata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"language_iso3\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlower\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 46\u001b[0m \u001b[0mmetadata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 47\u001b[1;33m \u001b[0mguid\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"doi\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 48\u001b[0m )\n\u001b[0;32m 49\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mdocument\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/srv/gargantext/parsing/FileParsers/FileParser.py\u001b[0m in \u001b[0;36mcreate_document\u001b[1;34m(self, parentNode, title, contents, language, metadata, guid)\u001b[0m\n\u001b[0;32m 100\u001b[0m \u001b[0mmetadata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmetadata\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 101\u001b[0m \u001b[1;31m#resource = resource,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 102\u001b[1;33m \u001b[0mparent\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mparentNode\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 103\u001b[0m )\n\u001b[0;32m 104\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/alexandre/projets/gargantext.py/env/lib/python3.4/site-packages/django/db/models/base.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 403\u001b[0m \u001b[1;31m# \"user_id\") so that the object gets properly cached (and type\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 404\u001b[0m \u001b[1;31m# checked) by the RelatedObjectDescriptor.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 405\u001b[1;33m \u001b[0msetattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfield\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrel_obj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 406\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 407\u001b[0m \u001b[0msetattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfield\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mattname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mval\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32m/home/alexandre/projets/gargantext.py/env/lib/python3.4/site-packages/django/db/models/fields/related.py\u001b[0m in \u001b[0;36m__set__\u001b[1;34m(self, instance, value)\u001b[0m\n\u001b[0;32m 337\u001b[0m raise ValueError('Cannot assign \"%r\": \"%s.%s\" must be a \"%s\" instance.' %\n\u001b[0;32m 338\u001b[0m (value, instance._meta.object_name,\n\u001b[1;32m--> 339\u001b[1;33m self.field.name, self.field.rel.to._meta.object_name))\n\u001b[0m\u001b[0;32m 340\u001b[0m \u001b[1;32melif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 341\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0minstance\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_state\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdb\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mValueError\u001b[0m: Cannot assign \"24\": \"Node.user\" must be a \"User\" instance."
]
}
],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"node.children.all()"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
\ No newline at end of file
parsing/FileParsers/FileParser.py
View file @ 281d7703
import collections
from node.models import Node, NodeType, Language
class NgramCache:
"""
......@@ -45,10 +45,10 @@ class FileParser:
self._ngramcaches = NgramCaches()
# extractors
self._extractors = dict()
self._document_nodetype = NodeType.get(name='Document')
with Language.objects.all() as languages:
self._languages_iso2 = {language.iso2.lower(): language for language in Language}
self._languages_iso3 = {language.iso3.lower(): language for language in Language}
self._document_nodetype = NodeType.objects.get(name='Document')
languages = Language.objects.all()
self._languages_iso2 = {language.iso2.lower(): language for language in languages}
self._languages_iso3 = {language.iso3.lower(): language for language in languages}
#self.parse()
"""Extract the ngrams from a given text.
......@@ -80,17 +80,17 @@ class FileParser:
"""
def create_document(self, parentNode, title, contents, language, metadata, guid=None):
# create or retrieve a resource for that document, based on its user id
if guid is None:
resource = Resource(guid=guid)
else:
try:
resource = Resource.get(guid=guid)
except:
resource = Resource(guid=guid)
# If the parent node already has a child with this resource, pass
# (is it a good thing?)
if parentNode.descendants().filter(resource=resource).exists():
return None
# if guid is None:
# resource = Resource(guid=guid)
# else:
# try:
# resource = Resource.get(guid=guid)
# except:
# resource = Resource(guid=guid)
# # If the parent node already has a child with this resource, pass
# # (is it a good thing?)
# if parentNode.descendants().filter(resource=resource).exists():
# return None
# create the document itself
childNode = Node(
user = parentNode.pk,
......@@ -98,7 +98,7 @@ class FileParser:
name = title,
language = language,
metadata = metadata,
resource = resource,
#resource = resource,
parent = parentNode
)
......
parsing/FileParsers/PubmedFileParser.py
View file @ 281d7703
from django.db import transaction
from lxml import etree
from parsing.FileParsers.FileParser import FileParser
import zipfile
import datetime
class PubmedFileParser(FileParser):
def parse(self, parentNode, tag=True):
# open the file as XML
xml_parser = etree.XMLParser(resolve_entities=False, recover=True)
xml = etree.parse(self._file, parser=xml_parser)
# parse all the articles, one by one
# all database operations should be performed within one transaction
xml_articles = xml.findall('PubmedArticle')
documents = []
with transaction.atomic():
for xml_article in xml_articles:
# extract data from the document
date_year = int(xml_article.find('MedlineCitation/DateCreated/Year').text)
date_month = int(xml_article.find('MedlineCitation/DateCreated/Month').text)
date_day = int(xml_article.find('MedlineCitation/DateCreated/Day').text)
metadata = {
# other metadata should also be included:
# authors, submission date, etc.
"date_pub": datetime.date(year, month, day),
"journal": xml_article.find('MedlineCitation/Article/Journal/Title').text,
"title": xml_article.find('MedlineCitation/Article/ArticleTitle').text,
"language_iso3": xml_article.find('MedlineCitation/Article/Language').text,
"doi": xml_article.find('PubmedData/ArticleIdList/ArticleId[type=doi]').text
}
contents = xml_article.find('MedlineCitation/Article/Abstract/AbstractText').text
# create the document in the database
document = self.create_document(
parentNode = parentNode,
title = metadata["title"],
contents = contents,
language = self._languages_iso3[metadata["language"].lower()],
metadata = metadata,
guid = metadata["doi"],
)
if document:
documents.append(document)
with zipfile.ZipFile(self._file) as zipFile:
for filename in zipFile.namelist():
file = zipFile.open(filename, "r")
# print(file.read())
xml = etree.parse(file, parser=xml_parser)
# parse all the articles, one by one
# all database operations should be performed within one transaction
xml_articles = xml.findall('PubmedArticle')
for xml_article in xml_articles:
# extract data from the document
date_year = int(xml_article.find('MedlineCitation/DateCreated/Year').text)
date_month = int(xml_article.find('MedlineCitation/DateCreated/Month').text)
date_day = int(xml_article.find('MedlineCitation/DateCreated/Day').text)
metadata = {
# other metadata should also be included:
# authors, submission date, etc.
"date_pub": datetime.date(date_year, date_month, date_day),
"journal": xml_article.find('MedlineCitation/Article/Journal/Title').text,
"title": xml_article.find('MedlineCitation/Article/ArticleTitle').text,
"language_iso3": xml_article.find('MedlineCitation/Article/Language').text,
# "doi": xml_article.find('PubmedData/ArticleIdList/ArticleId[type=doi]').text
"doi": "poiopipoiopip"
}
contents = xml_article.find('MedlineCitation/Article/Abstract/AbstractText').text
# create the document in the database
document = self.create_document(
parentNode = parentNode,
title = metadata["title"],
contents = contents,
language = self._languages_iso3[metadata["language_iso3"].lower()],
metadata = metadata,
guid = metadata["doi"],
)
if document:
documents.append(document)
return documents
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment