diff --git a/html_text/README.rst b/html_text/README.rst new file mode 100644 index 000000000..b70b6fbfd --- /dev/null +++ b/html_text/README.rst @@ -0,0 +1,119 @@ +==================== +Text from HTML field +==================== + +.. !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! + !! This file is generated by oca-gen-addon-readme !! + !! changes will be overwritten. !! + !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! + +.. |badge1| image:: https://img.shields.io/badge/maturity-Beta-yellow.png + :target: https://odoo-community.org/page/development-status + :alt: Beta +.. |badge2| image:: https://img.shields.io/badge/licence-AGPL--3-blue.png + :target: http://www.gnu.org/licenses/agpl-3.0-standalone.html + :alt: License: AGPL-3 +.. |badge3| image:: https://img.shields.io/badge/github-OCA%2Fserver--tools-lightgray.png?logo=github + :target: https://github.com/OCA/server-tools/tree/14.0/html_text + :alt: OCA/server-tools +.. |badge4| image:: https://img.shields.io/badge/weblate-Translate%20me-F47D42.png + :target: https://translation.odoo-community.org/projects/server-tools-14-0/server-tools-14-0-html_text + :alt: Translate me on Weblate +.. |badge5| image:: https://img.shields.io/badge/runbot-Try%20me-875A7B.png + :target: https://runbot.odoo-community.org/runbot/149/14.0 + :alt: Try me on Runbot + +|badge1| |badge2| |badge3| |badge4| |badge5| + +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. + +**Table of contents** + +.. contents:: + :local: + +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:: + + 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:: + + + +.. image:: https://odoo-community.org/website/image/ir.attachment/5784_f2813bd/datas + :alt: Try me on Runbot + :target: https://runbot.odoo-community.org/runbot/149/11.0 + +Known issues / Roadmap +====================== + +* An option could be added to try to respect the basic HTML tags inside the + excerpt (````, ````, ``

``, etc.). + +Bug Tracker +=========== + +Bugs are tracked on `GitHub 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 `_. + +Do not contact contributors directly about support or help with technical issues. + +Credits +======= + +Authors +~~~~~~~ + +* Grupo ESOC Ingeniería de Servicios +* Tecnativa +* Onestein + +Contributors +~~~~~~~~~~~~ + +* Dennis Sluijk +* `Tecnativa `_:", +* Helly kapatel +* Mantas Šniukas + + * Jairo Llopis + * Vicent Cubells + * Víctor Martínez + +Maintainers +~~~~~~~~~~~ + +This module is maintained by the OCA. + +.. image:: https://odoo-community.org/logo.png + :alt: Odoo Community Association + :target: https://odoo-community.org + +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. + +This module is part of the `OCA/server-tools `_ project on GitHub. + +You are welcome to contribute. To learn how please visit https://odoo-community.org/page/Contribute. diff --git a/html_text/__init__.py b/html_text/__init__.py new file mode 100644 index 000000000..31660d6a9 --- /dev/null +++ b/html_text/__init__.py @@ -0,0 +1,3 @@ +# License AGPL-3.0 or later (https://www.gnu.org/licenses/agpl). + +from . import models diff --git a/html_text/__manifest__.py b/html_text/__manifest__.py new file mode 100644 index 000000000..746e99635 --- /dev/null +++ b/html_text/__manifest__.py @@ -0,0 +1,19 @@ +# Copyright 2016-2017 Jairo Llopis +# Copyright 2016 Tecnativa - Vicent Cubells +# License AGPL-3.0 or later (https://www.gnu.org/licenses/agpl). +{ + "name": "Text from HTML field", + "summary": "Generate excerpts from any HTML field", + "version": "15.0.1.0.0", + "category": "Tools", + "website": "https://github.com/OCA/server-tools", + "author": "Grupo ESOC Ingeniería de Servicios, " + "Tecnativa, " + "Onestein, " + "Odoo Community Association (OCA)", + "license": "AGPL-3", + "application": False, + "installable": True, + "external_dependencies": {"python": ["lxml"]}, + "depends": ["base"], +} diff --git a/html_text/i18n/ca.po b/html_text/i18n/ca.po new file mode 100644 index 000000000..b82487c21 --- /dev/null +++ b/html_text/i18n/ca.po @@ -0,0 +1,45 @@ +# Translation of Odoo Server. +# This file contains the translation of the following modules: +# * html_text +# +# Translators: +# Marc Tormo i Bochaca , 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 , 2017\n" +"Language-Team: Catalan (https://www.transifex.com/oca/teams/23907/ca/)\n" +"Language: ca\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: \n" +"Plural-Forms: nplurals=2; plural=(n != 1);\n" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__display_name +msgid "Display Name" +msgstr "" + +#. module: html_text +#: model:ir.model,name:html_text.model_ir_fields_converter +#, fuzzy +msgid "Fields Converter" +msgstr "ir.fields.converter" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__id +msgid "ID" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter____last_update +msgid "Last Modified on" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__smart_search +msgid "Smart Search" +msgstr "" diff --git a/html_text/i18n/de.po b/html_text/i18n/de.po new file mode 100644 index 000000000..e75d5aa47 --- /dev/null +++ b/html_text/i18n/de.po @@ -0,0 +1,45 @@ +# Translation of Odoo Server. +# This file contains the translation of the following modules: +# * html_text +# +# Translators: +# Rudolf Schnapka , 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 , 2017\n" +"Language-Team: German (https://www.transifex.com/oca/teams/23907/de/)\n" +"Language: de\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: \n" +"Plural-Forms: nplurals=2; plural=(n != 1);\n" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__display_name +msgid "Display Name" +msgstr "" + +#. module: html_text +#: model:ir.model,name:html_text.model_ir_fields_converter +#, fuzzy +msgid "Fields Converter" +msgstr "ir.fields.converter" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__id +msgid "ID" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter____last_update +msgid "Last Modified on" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__smart_search +msgid "Smart Search" +msgstr "" diff --git a/html_text/i18n/es.po b/html_text/i18n/es.po new file mode 100644 index 000000000..d32bd69b4 --- /dev/null +++ b/html_text/i18n/es.po @@ -0,0 +1,45 @@ +# Translation of Odoo Server. +# This file contains the translation of the following modules: +# * html_text +# +# Translators: +# Pedro M. Baeza , 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: 2021-03-19 17:46+0000\n" +"Last-Translator: Ana Suárez \n" +"Language-Team: Spanish (https://www.transifex.com/oca/teams/23907/es/)\n" +"Language: es\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: \n" +"Plural-Forms: nplurals=2; plural=n != 1;\n" +"X-Generator: Weblate 4.3.2\n" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__display_name +msgid "Display Name" +msgstr "" + +#. module: html_text +#: model:ir.model,name:html_text.model_ir_fields_converter +msgid "Fields Converter" +msgstr "Convertidor de Campos" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__id +msgid "ID" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter____last_update +msgid "Last Modified on" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__smart_search +msgid "Smart Search" +msgstr "" diff --git a/html_text/i18n/es_ES.po b/html_text/i18n/es_ES.po new file mode 100644 index 000000000..b6e252571 --- /dev/null +++ b/html_text/i18n/es_ES.po @@ -0,0 +1,46 @@ +# Translation of Odoo Server. +# This file contains the translation of the following modules: +# * html_text +# +# Translators: +# Fernando Lara , 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 , 2017\n" +"Language-Team: Spanish (Spain) (https://www.transifex.com/oca/teams/23907/" +"es_ES/)\n" +"Language: es_ES\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: \n" +"Plural-Forms: nplurals=2; plural=(n != 1);\n" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__display_name +msgid "Display Name" +msgstr "" + +#. module: html_text +#: model:ir.model,name:html_text.model_ir_fields_converter +#, fuzzy +msgid "Fields Converter" +msgstr "ir.documentos.conversor" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__id +msgid "ID" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter____last_update +msgid "Last Modified on" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__smart_search +msgid "Smart Search" +msgstr "" diff --git a/html_text/i18n/hr.po b/html_text/i18n/hr.po new file mode 100644 index 000000000..a0cc5ac2f --- /dev/null +++ b/html_text/i18n/hr.po @@ -0,0 +1,43 @@ +# Translation of Odoo Server. +# This file contains the translation of the following modules: +# * html_text +# +msgid "" +msgstr "" +"Project-Id-Version: Odoo Server 12.0\n" +"Report-Msgid-Bugs-To: \n" +"PO-Revision-Date: 2019-11-13 17:34+0000\n" +"Last-Translator: Bole \n" +"Language-Team: none\n" +"Language: hr\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: \n" +"Plural-Forms: nplurals=3; plural=n%10==1 && n%100!=11 ? 0 : n%10>=2 && n" +"%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2;\n" +"X-Generator: Weblate 3.8\n" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__display_name +msgid "Display Name" +msgstr "" + +#. module: html_text +#: model:ir.model,name:html_text.model_ir_fields_converter +msgid "Fields Converter" +msgstr "Pretvaranje polja" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__id +msgid "ID" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter____last_update +msgid "Last Modified on" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__smart_search +msgid "Smart Search" +msgstr "" diff --git a/html_text/i18n/html_text.pot b/html_text/i18n/html_text.pot new file mode 100644 index 000000000..382577d81 --- /dev/null +++ b/html_text/i18n/html_text.pot @@ -0,0 +1,39 @@ +# Translation of Odoo Server. +# This file contains the translation of the following modules: +# * html_text +# +msgid "" +msgstr "" +"Project-Id-Version: Odoo Server 14.0\n" +"Report-Msgid-Bugs-To: \n" +"Last-Translator: \n" +"Language-Team: \n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: \n" +"Plural-Forms: \n" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__display_name +msgid "Display Name" +msgstr "" + +#. module: html_text +#: model:ir.model,name:html_text.model_ir_fields_converter +msgid "Fields Converter" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__id +msgid "ID" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter____last_update +msgid "Last Modified on" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__smart_search +msgid "Smart Search" +msgstr "" diff --git a/html_text/i18n/it.po b/html_text/i18n/it.po new file mode 100644 index 000000000..1c4d41231 --- /dev/null +++ b/html_text/i18n/it.po @@ -0,0 +1,45 @@ +# Translation of Odoo Server. +# This file contains the translation of the following modules: +# * html_text +# +# Translators: +# Paolo Valier , 2018 +msgid "" +msgstr "" +"Project-Id-Version: Odoo Server 10.0\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2018-01-06 02:25+0000\n" +"PO-Revision-Date: 2018-01-06 02:25+0000\n" +"Last-Translator: Paolo Valier , 2018\n" +"Language-Team: Italian (https://www.transifex.com/oca/teams/23907/it/)\n" +"Language: it\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: \n" +"Plural-Forms: nplurals=2; plural=(n != 1);\n" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__display_name +msgid "Display Name" +msgstr "" + +#. module: html_text +#: model:ir.model,name:html_text.model_ir_fields_converter +#, fuzzy +msgid "Fields Converter" +msgstr "ir.fields.converter" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__id +msgid "ID" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter____last_update +msgid "Last Modified on" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__smart_search +msgid "Smart Search" +msgstr "" diff --git a/html_text/i18n/tr.po b/html_text/i18n/tr.po new file mode 100644 index 000000000..c5d8d9aa8 --- /dev/null +++ b/html_text/i18n/tr.po @@ -0,0 +1,45 @@ +# Translation of Odoo Server. +# This file contains the translation of the following modules: +# * html_text +# +# Translators: +# Ahmet Altinisik , 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 , 2016\n" +"Language-Team: Turkish (https://www.transifex.com/oca/teams/23907/tr/)\n" +"Language: tr\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: \n" +"Plural-Forms: nplurals=2; plural=(n > 1);\n" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__display_name +msgid "Display Name" +msgstr "" + +#. module: html_text +#: model:ir.model,name:html_text.model_ir_fields_converter +#, fuzzy +msgid "Fields Converter" +msgstr "ir.fields.converter" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__id +msgid "ID" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter____last_update +msgid "Last Modified on" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__smart_search +msgid "Smart Search" +msgstr "" diff --git a/html_text/i18n/zh_CN.po b/html_text/i18n/zh_CN.po new file mode 100644 index 000000000..7aea0bc70 --- /dev/null +++ b/html_text/i18n/zh_CN.po @@ -0,0 +1,42 @@ +# Translation of Odoo Server. +# This file contains the translation of the following modules: +# * html_text +# +msgid "" +msgstr "" +"Project-Id-Version: Odoo Server 12.0\n" +"Report-Msgid-Bugs-To: \n" +"PO-Revision-Date: 2019-08-31 06:18+0000\n" +"Last-Translator: 黎伟杰 <674416404@qq.com>\n" +"Language-Team: none\n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: \n" +"Plural-Forms: nplurals=1; plural=0;\n" +"X-Generator: Weblate 3.8\n" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__display_name +msgid "Display Name" +msgstr "" + +#. module: html_text +#: model:ir.model,name:html_text.model_ir_fields_converter +msgid "Fields Converter" +msgstr "字段转换器" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__id +msgid "ID" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter____last_update +msgid "Last Modified on" +msgstr "" + +#. module: html_text +#: model:ir.model.fields,field_description:html_text.field_ir_fields_converter__smart_search +msgid "Smart Search" +msgstr "" diff --git a/html_text/models/__init__.py b/html_text/models/__init__.py new file mode 100644 index 000000000..e21238ee9 --- /dev/null +++ b/html_text/models/__init__.py @@ -0,0 +1,3 @@ +# License AGPL-3.0 or later (https://www.gnu.org/licenses/agpl). + +from . import ir_fields_converter diff --git a/html_text/models/ir_fields_converter.py b/html_text/models/ir_fields_converter.py new file mode 100644 index 000000000..7a07a359d --- /dev/null +++ b/html_text/models/ir_fields_converter.py @@ -0,0 +1,74 @@ +# Copyright 2016-2017 Jairo Llopis +# Copyright 2016 Tecnativa - Vicent Cubells +# License AGPL-3.0 or later (https://www.gnu.org/licenses/agpl). + +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 diff --git a/html_text/readme/CONTRIBUTORS.rst b/html_text/readme/CONTRIBUTORS.rst new file mode 100644 index 000000000..cb155b7d8 --- /dev/null +++ b/html_text/readme/CONTRIBUTORS.rst @@ -0,0 +1,8 @@ +* Dennis Sluijk +* `Tecnativa `_:", +* Helly kapatel +* Mantas Šniukas + + * Jairo Llopis + * Vicent Cubells + * Víctor Martínez diff --git a/html_text/readme/DESCRIPTION.rst b/html_text/readme/DESCRIPTION.rst new file mode 100644 index 000000000..579fd7667 --- /dev/null +++ b/html_text/readme/DESCRIPTION.rst @@ -0,0 +1,7 @@ +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. diff --git a/html_text/readme/ROADMAP.rst b/html_text/readme/ROADMAP.rst new file mode 100644 index 000000000..0a77fddef --- /dev/null +++ b/html_text/readme/ROADMAP.rst @@ -0,0 +1,2 @@ +* An option could be added to try to respect the basic HTML tags inside the + excerpt (````, ````, ``

``, etc.). diff --git a/html_text/readme/USAGE.rst b/html_text/readme/USAGE.rst new file mode 100644 index 000000000..ae34a9b25 --- /dev/null +++ b/html_text/readme/USAGE.rst @@ -0,0 +1,21 @@ +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:: + + 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:: + + + +.. image:: https://odoo-community.org/website/image/ir.attachment/5784_f2813bd/datas + :alt: Try me on Runbot + :target: https://runbot.odoo-community.org/runbot/149/11.0 diff --git a/html_text/static/description/icon.png b/html_text/static/description/icon.png new file mode 100644 index 000000000..3a0328b51 Binary files /dev/null and b/html_text/static/description/icon.png differ diff --git a/html_text/static/description/index.html b/html_text/static/description/index.html new file mode 100644 index 000000000..b626cc6ca --- /dev/null +++ b/html_text/static/description/index.html @@ -0,0 +1,463 @@ + + + + + + +Text from HTML field + + + +

+

Text from HTML field

+ + +

Beta License: AGPL-3 OCA/server-tools Translate me on Weblate Try me on Runbot

+

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.

+

Table of contents

+ +
+

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:

+
+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)"/>
+
+Try me on Runbot +
+
+

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. +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.

+

Do not contact contributors directly about support or help with technical issues.

+
+
+

Credits

+
+

Authors

+
    +
  • Grupo ESOC Ingeniería de Servicios
    • +
  • Tecnativa
    • +
  • Onestein
    • +
+
+
+

Contributors

+ +
+
+

Maintainers

+

This module is maintained by the OCA.

+Odoo Community Association +

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.

+

This module is part of the OCA/server-tools project on GitHub.

+

You are welcome to contribute. To learn how please visit https://odoo-community.org/page/Contribute.

+
+
+
+ + diff --git a/html_text/tests/__init__.py b/html_text/tests/__init__.py new file mode 100644 index 000000000..d9d2b331a --- /dev/null +++ b/html_text/tests/__init__.py @@ -0,0 +1,3 @@ +# License AGPL-3.0 or later (https://www.gnu.org/licenses/agpl). + +from . import test_extractor diff --git a/html_text/tests/test_extractor.py b/html_text/tests/test_extractor.py new file mode 100644 index 000000000..8036eace4 --- /dev/null +++ b/html_text/tests/test_extractor.py @@ -0,0 +1,56 @@ +# Copyright 2016-2017 Jairo Llopis +# License AGPL-3.0 or later (https://www.gnu.org/licenses/agpl). + +from lxml import etree + +from odoo.tests.common import TransactionCase +from odoo.tools import mute_logger + + +class ExtractorCase(TransactionCase): + def setUp(self): + super().setUp() + # Shortcut + self.text_from_html = self.env["ir.fields.converter"].text_from_html + + def test_excerpts(self): + """Text gets correctly extracted.""" + html = u""" + + +
+

I'm a title

+

I'm a paragraph

+ ¡Pues yo soy español! +
+ + + """ + 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("odoo.addons.html_text.models.ir_fields_converter") + def test_empty_html(self): + """Empty HTML handled correctly.""" + self.assertEqual(self.text_from_html(""), "") + with self.assertRaises(etree.ParserError): + self.text_from_html("", fail=True) + + @mute_logger("odoo.addons.html_text.models.ir_fields_converter") + 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) diff --git a/requirements.txt b/requirements.txt index 7a9599183..21bd1f228 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,5 +1,6 @@ # generated from manifests external_dependencies dataclasses +lxml mako odoorpc openupgradelib diff --git a/setup/html_text/odoo/addons/html_text b/setup/html_text/odoo/addons/html_text new file mode 120000 index 000000000..a8751217b --- /dev/null +++ b/setup/html_text/odoo/addons/html_text @@ -0,0 +1 @@ +../../../../html_text \ No newline at end of file diff --git a/setup/html_text/setup.py b/setup/html_text/setup.py new file mode 100644 index 000000000..28c57bb64 --- /dev/null +++ b/setup/html_text/setup.py @@ -0,0 +1,6 @@ +import setuptools + +setuptools.setup( + setup_requires=['setuptools-odoo'], + odoo_addon=True, +)