Browse Source

Merge pull request #874 from Tecnativa/10.0-html_text

[MIG][10.0][html_text] Migrate
pull/882/head
Pedro M. Baeza 8 years ago
committed by GitHub
parent
commit
120ba68a00
  1. 79
      html_text/README.rst
  2. 4
      html_text/__init__.py
  3. 25
      html_text/__manifest__.py
  4. 24
      html_text/i18n/ca.po
  5. 24
      html_text/i18n/de.po
  6. 24
      html_text/i18n/es.po
  7. 24
      html_text/i18n/es_ES.po
  8. 24
      html_text/i18n/tr.po
  9. 4
      html_text/models/__init__.py
  10. 73
      html_text/models/ir_fields_converter.py
  11. BIN
      html_text/static/description/icon.png
  12. 4
      html_text/tests/__init__.py
  13. 63
      html_text/tests/test_extractor.py

79
html_text/README.rst

@ -0,0 +1,79 @@
.. image:: https://img.shields.io/badge/licence-AGPL--3-blue.svg
:target: http://www.gnu.org/licenses/agpl-3.0-standalone.html
:alt: License: AGPL-3
====================
Text from HTML field
====================
This module provides some technical features that allow to extract text from
any chunk of HTML, without HTML tags or attributes. You can chose either:
* To truncate the result by amount of words or characters.
* To append an ellipsis (or any character(s)) at the end of the result.
It can be used to easily generate excerpts.
Usage
=====
This module just adds a technical utility, but nothing for the end user.
If you are a developer and need this utility for your module, see these
examples and read the docs inside the code.
Python example::
@api.multi
def some_method(self):
# Get truncated text from an HTML field. It will 40 words and 100
# characters at most, and will have "..." appended at the end if it
# gets truncated.
truncated_text = self.env["ir.fields.converter"].text_from_html(
self.html_field, 40, 100, "...")
QWeb example::
<t t-esc="env['ir.fields.converter'].text_from_html(doc.html_field)"/>
.. image:: https://odoo-community.org/website/image/ir.attachment/5784_f2813bd/datas
:alt: Try me on Runbot
:target: https://runbot.odoo-community.org/runbot/149/10.0
Known issues / Roadmap
======================
* An option could be added to try to respect the basic HTML tags inside the
excerpt (``<b>``, ``<i>``, ``<p>``, etc.).
Bug Tracker
===========
Bugs are tracked on `GitHub Issues
<https://github.com/OCA/server-tools/issues>`_. In case of trouble, please
check there if your issue has already been reported. If you spotted it first,
help us smashing it by providing a detailed and welcomed feedback.
Credits
=======
Contributors
------------
* Jairo Llopis <yajo.sk8@gmail.com>
* Vicent Cubells <vicent.cubells@tecnativa.com>
Maintainer
----------
.. image:: https://odoo-community.org/logo.png
:alt: Odoo Community Association
:target: https://odoo-community.org
This module is maintained by the OCA.
OCA, or the Odoo Community Association, is a nonprofit organization whose
mission is to support the collaborative development of Odoo features and
promote its widespread use.
To contribute to this module, please visit https://odoo-community.org.

4
html_text/__init__.py

@ -0,0 +1,4 @@
# -*- coding: utf-8 -*-
# License AGPL-3.0 or later (http://www.gnu.org/licenses/agpl.html).
from . import models

25
html_text/__manifest__.py

@ -0,0 +1,25 @@
# -*- coding: utf-8 -*-
# Copyright 2016-2017 Jairo Llopis <jairo.llopis@tecnativa.com>
# Copyright 2016 Tecnativa - Vicent Cubells
# License AGPL-3.0 or later (http://www.gnu.org/licenses/agpl.html).
{
"name": "Text from HTML field",
"summary": "Generate excerpts from any HTML field",
"version": "10.0.1.0.0",
"category": "Tools",
"website": "https://tecnativa.com",
"author": "Grupo ESOC Ingeniería de Servicios, "
"Tecnativa, "
"Odoo Community Association (OCA)",
"license": "AGPL-3",
"application": False,
"installable": True,
"external_dependencies": {
"python": [
"lxml.html",
],
},
"depends": [
"base",
],
}

24
html_text/i18n/ca.po

@ -0,0 +1,24 @@
# Translation of Odoo Server.
# This file contains the translation of the following modules:
# * html_text
#
# Translators:
# Marc Tormo i Bochaca <mtbochaca@gmail.com>, 2017
msgid ""
msgstr ""
"Project-Id-Version: Odoo Server 9.0c\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2017-04-19 18:00+0000\n"
"PO-Revision-Date: 2017-04-19 18:00+0000\n"
"Last-Translator: Marc Tormo i Bochaca <mtbochaca@gmail.com>, 2017\n"
"Language-Team: Catalan (https://www.transifex.com/oca/teams/23907/ca/)\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: \n"
"Language: ca\n"
"Plural-Forms: nplurals=2; plural=(n != 1);\n"
#. module: html_text
#: model:ir.model,name:html_text.model_ir_fields_converter
msgid "ir.fields.converter"
msgstr "ir.fields.converter"

24
html_text/i18n/de.po

@ -0,0 +1,24 @@
# Translation of Odoo Server.
# This file contains the translation of the following modules:
# * html_text
#
# Translators:
# Rudolf Schnapka <rs@techno-flex.de>, 2017
msgid ""
msgstr ""
"Project-Id-Version: Odoo Server 9.0c\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2017-04-19 18:00+0000\n"
"PO-Revision-Date: 2017-04-19 18:00+0000\n"
"Last-Translator: Rudolf Schnapka <rs@techno-flex.de>, 2017\n"
"Language-Team: German (https://www.transifex.com/oca/teams/23907/de/)\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: \n"
"Language: de\n"
"Plural-Forms: nplurals=2; plural=(n != 1);\n"
#. module: html_text
#: model:ir.model,name:html_text.model_ir_fields_converter
msgid "ir.fields.converter"
msgstr "ir.fields.converter"

24
html_text/i18n/es.po

@ -0,0 +1,24 @@
# Translation of Odoo Server.
# This file contains the translation of the following modules:
# * html_text
#
# Translators:
# Pedro M. Baeza <pedro.baeza@gmail.com>, 2016
msgid ""
msgstr ""
"Project-Id-Version: Odoo Server 9.0c\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2016-12-17 02:07+0000\n"
"PO-Revision-Date: 2016-12-17 02:07+0000\n"
"Last-Translator: Pedro M. Baeza <pedro.baeza@gmail.com>, 2016\n"
"Language-Team: Spanish (https://www.transifex.com/oca/teams/23907/es/)\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: \n"
"Language: es\n"
"Plural-Forms: nplurals=2; plural=(n != 1);\n"
#. module: html_text
#: model:ir.model,name:html_text.model_ir_fields_converter
msgid "ir.fields.converter"
msgstr "ir.fields.converter"

24
html_text/i18n/es_ES.po

@ -0,0 +1,24 @@
# Translation of Odoo Server.
# This file contains the translation of the following modules:
# * html_text
#
# Translators:
# Fernando Lara <gennesis45@gmail.com>, 2017
msgid ""
msgstr ""
"Project-Id-Version: Odoo Server 9.0c\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2017-02-16 10:39+0000\n"
"PO-Revision-Date: 2017-02-16 10:39+0000\n"
"Last-Translator: Fernando Lara <gennesis45@gmail.com>, 2017\n"
"Language-Team: Spanish (Spain) (https://www.transifex.com/oca/teams/23907/es_ES/)\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: \n"
"Language: es_ES\n"
"Plural-Forms: nplurals=2; plural=(n != 1);\n"
#. module: html_text
#: model:ir.model,name:html_text.model_ir_fields_converter
msgid "ir.fields.converter"
msgstr "ir.documentos.conversor"

24
html_text/i18n/tr.po

@ -0,0 +1,24 @@
# Translation of Odoo Server.
# This file contains the translation of the following modules:
# * html_text
#
# Translators:
# Ahmet Altinisik <aaltinisik@altinkaya.com.tr>, 2016
msgid ""
msgstr ""
"Project-Id-Version: Odoo Server 9.0c\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2016-12-29 03:40+0000\n"
"PO-Revision-Date: 2016-12-29 03:40+0000\n"
"Last-Translator: Ahmet Altinisik <aaltinisik@altinkaya.com.tr>, 2016\n"
"Language-Team: Turkish (https://www.transifex.com/oca/teams/23907/tr/)\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: \n"
"Language: tr\n"
"Plural-Forms: nplurals=2; plural=(n > 1);\n"
#. module: html_text
#: model:ir.model,name:html_text.model_ir_fields_converter
msgid "ir.fields.converter"
msgstr "ir.fields.converter"

4
html_text/models/__init__.py

@ -0,0 +1,4 @@
# -*- coding: utf-8 -*-
# License AGPL-3.0 or later (http://www.gnu.org/licenses/agpl.html).
from . import ir_fields_converter

73
html_text/models/ir_fields_converter.py

@ -0,0 +1,73 @@
# -*- coding: utf-8 -*-
# Copyright 2016-2017 Jairo Llopis <jairo.llopis@tecnativa.com>
# Copyright 2016 Tecnativa - Vicent Cubells
# License AGPL-3.0 or later (http://www.gnu.org/licenses/agpl.html).
import logging
from lxml import etree, html
from odoo import api, models
_logger = logging.getLogger(__name__)
class IrFieldsConverter(models.AbstractModel):
_inherit = "ir.fields.converter"
@api.model
def text_from_html(self, html_content, max_words=None, max_chars=None,
ellipsis=u"", fail=False):
"""Extract text from an HTML field in a generator.
:param str html_content:
HTML contents from where to extract the text.
:param int max_words:
Maximum amount of words allowed in the resulting string.
:param int max_chars:
Maximum amount of characters allowed in the resulting string. If
you apply this limit, beware that the last word could get cut in an
unexpected place.
:param str ellipsis:
Character(s) to be appended to the end of the resulting string if
it gets truncated after applying limits set in :param:`max_words`
or :param:`max_chars`. If you want nothing applied, just set an
empty string.
:param bool fail:
If ``True``, exceptions will be raised. Otherwise, an empty string
will be returned on failure.
"""
# Parse HTML
try:
doc = html.fromstring(html_content)
except (TypeError, etree.XMLSyntaxError, etree.ParserError):
if fail:
raise
else:
_logger.exception("Failure parsing this HTML:\n%s",
html_content)
return ""
# Get words
words = u"".join(doc.xpath("//text()")).split()
# Truncate words
suffix = max_words and len(words) > max_words
if max_words:
words = words[:max_words]
# Get text
text = u" ".join(words)
# Truncate text
suffix = suffix or max_chars and len(text) > max_chars
if max_chars:
text = text[:max_chars - (len(ellipsis) if suffix else 0)].strip()
# Append ellipsis if needed
if suffix:
text += ellipsis
return text

BIN
html_text/static/description/icon.png

After

Width: 128  |  Height: 128  |  Size: 9.2 KiB

4
html_text/tests/__init__.py

@ -0,0 +1,4 @@
# -*- coding: utf-8 -*-
# License AGPL-3.0 or later (http://www.gnu.org/licenses/agpl.html).
from . import test_extractor

63
html_text/tests/test_extractor.py

@ -0,0 +1,63 @@
# -*- coding: utf-8 -*-
# Copyright 2016-2017 Jairo Llopis <jairo.llopis@tecnativa.com>
# License AGPL-3.0 or later (http://www.gnu.org/licenses/agpl.html).
from lxml import etree
from odoo.tools import mute_logger
from odoo.tests.common import TransactionCase
from ..models import ir_fields_converter
class ExtractorCase(TransactionCase):
def setUp(self):
super(ExtractorCase, self).setUp()
# Shortcut
self.text_from_html = self.env["ir.fields.converter"].text_from_html
def test_excerpts(self):
"""Text gets correctly extracted."""
html = u"""
<html>
<body>
<div class="this should not appear">
<h1>I'm a title</h1>
<p>I'm a paragraph</p>
<small>¡Pues yo soy español!</small>
</div>
</body>
</html>
"""
self.assertEqual(
self.text_from_html(html),
u"I'm a title I'm a paragraph ¡Pues yo soy español!")
self.assertEqual(
self.text_from_html(html, 8),
u"I'm a title I'm a paragraph ¡Pues yo…")
self.assertEqual(
self.text_from_html(html, 8, 31),
u"I'm a title I'm a paragraph ¡P…")
self.assertEqual(
self.text_from_html(html, 7, ellipsis=""),
u"I'm a title I'm a paragraph ¡Pues")
@mute_logger(ir_fields_converter.__name__)
def test_empty_html(self):
"""Empty HTML handled correctly."""
self.assertEqual(self.text_from_html(""), "")
with self.assertRaises(etree.XMLSyntaxError):
self.text_from_html("", fail=True)
@mute_logger(ir_fields_converter.__name__)
def test_false_html(self):
"""``False`` HTML handled correctly."""
self.assertEqual(self.text_from_html(False), "")
with self.assertRaises(TypeError):
self.text_from_html(False, fail=True)
@mute_logger(ir_fields_converter.__name__)
def test_bad_html(self):
"""Bad HTML handled correctly."""
self.assertEqual(self.text_from_html("<<bad>"), "")
with self.assertRaises(etree.ParserError):
self.text_from_html("<<bad>", fail=True)
Loading…
Cancel
Save