sporada/nopaque
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque.git synced 2025-06-14 18:10:40 +00:00
Code Issues Projects Releases Wiki Activity

Big update, corpus analysis reworked, versioned services, preliminary work for contributions

Browse Source
This commit is contained in:
Patrick Jentsch
2022-02-03 12:39:16 +01:00
parent 0647537192
commit fe938c0ca2
36 changed files with 1552 additions and 431 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
app/templates/_colors.html.j2
View File

@ -19,12 +19,12 @@
'darken': '#a1b300',
'lighten': '#f2f3e1'
},
'nlp': {
'spacy-nlp': {
'base': '#98acd2',
'darken': '#0064a3',
'lighten': '#e5e8f5'
},
'ocr': {
'tesseract-ocr': {
'base': '#a9d8c8',
'darken': '#00a58b',
'lighten': '#e7f4f1'

7
app/templates/_sidenav.html.j2
View File

@ -15,8 +15,8 @@
<li><div class="divider"></div></li>
<li><a class="subheader">Processes & Services</a></li>
<li class="service-color service-color-border border-darken" data-service="file-setup" style="border-left: 10px solid; margin-top: 5px;"><a href="{{ url_for('services.service', service='file-setup') }}"><i class="nopaque-icons service-icon" data-service="file-setup"></i>File setup</a></li>
<li class="service-color service-color-border border-darken" data-service="ocr" style="border-left: 10px solid; margin-top: 5px;"><a href="{{ url_for('services.service', service='ocr') }}"><i class="nopaque-icons service-icon" data-service="ocr"></i>OCR</a></li>
<li class="service-color service-color-border border-darken" data-service="nlp" style="border-left: 10px solid; margin-top: 5px;"><a href="{{ url_for('services.service', service='nlp') }}"><i class="nopaque-icons service-icon" data-service="nlp"></i>NLP</a></li>
<li class="service-color service-color-border border-darken" data-service="tesseract-ocr" style="border-left: 10px solid; margin-top: 5px;"><a href="{{ url_for('services.service', service='tesseract-ocr') }}"><i class="nopaque-icons service-icon" data-service="tesseract-ocr"></i>OCR</a></li>
<li class="service-color service-color-border border-darken" data-service="spacy-nlp" style="border-left: 10px solid; margin-top: 5px;"><a href="{{ url_for('services.service', service='spacy-nlp') }}"><i class="nopaque-icons service-icon" data-service="spacy-nlp"></i>NLP</a></li>
<li class="service-color service-color-border border-darken" data-service="corpus-analysis" style="border-left: 10px solid; margin-top: 5px;"><a href="{{ url_for('services.service', service='corpus-analysis') }}"><i class="nopaque-icons service-icon" data-service="corpus-analysis"></i>Corpus analysis</a></li>
<li><div class="divider"></div></li>
<li><a class="subheader">Account</a></li>
@ -28,6 +28,9 @@
{% if current_user.can(Permission.ADMINISTRATE) %}
<li><a href="{{ url_for('admin.index') }}"><i class="material-icons">admin_panel_settings</i>Administration</a></li>
{% endif %}
{% if current_user.can(Permission.CONTRIBUTE) %}
<li><a href="{{ url_for('contribute.index') }}"><i class="material-icons">new_label</i>Contribute</a></li>
{% endif %}
{% if current_user.can(Permission.USE_API) %}
<li><a href="{{ url_for('api.doc') }}"><i class="material-icons">api</i>API</a></li>
{% endif %}

18
app/templates/main/dashboard.html.j2
View File

@ -120,32 +120,32 @@
</a>
<br><br>
<p class="service-color-text darken" data-service="file-setup"><b>File setup</b></p>
<p class="light">Digital copies of text based research data (books, letters, etc.) often comprise various files and formats. nopaque converts and merges those files to facilitate further processing and the application of other services.</p>
<p class="light">Digital copies of text based research data (books, letters, etc.) often comprise various files and formats. nopaque converts and merges those files to facilitate further processing.</p>
<a href="{{ url_for('services.service', service='file-setup') }}" class="waves-effect waves-light btn service-color darken" data-service="file-setup">Create Job</a>
</div>
</div>
<div class="col s12 m4">
<div class="card-panel center-align hoverable">
<br>
<a href="{{ url_for('services.service', service='ocr') }}" class="btn-floating btn-large waves-effect waves-light" style="transform: scale(2);">
<i class="nopaque-icons service-color darken service-icon" data-service="ocr" style="font-size: 2.5rem;"></i>
<a href="{{ url_for('services.service', service='tesseract-ocr') }}" class="btn-floating btn-large waves-effect waves-light" style="transform: scale(2);">
<i class="nopaque-icons service-color darken service-icon" data-service="tesseract-ocr" style="font-size: 2.5rem;"></i>
</a>
<br><br>
<p class="service-color-text darken" data-service="ocr"><b>Optical Character Recognition</b></p>
<p class="service-color-text darken" data-service="tesseract-ocr"><b>Optical Character Recognition</b></p>
<p class="light">nopaque converts your image data – like photos or scans – into text data through a process called OCR. This step enables you to proceed with further computational analysis of your documents.</p>
<a href="{{ url_for('services.service', service='ocr') }}" class="waves-effect waves-light btn service-color darken" data-service="ocr">Create Job</a>
<a href="{{ url_for('services.service', service='tesseract-ocr') }}" class="waves-effect waves-light btn service-color darken" data-service="tesseract-ocr">Create Job</a>
</div>
</div>
<div class="col s12 m4">
<div class="card-panel center-align hoverable">
<br>
<a href="{{ url_for('services.service', service='nlp') }}" class="btn-floating btn-large waves-effect waves-light" style="transform: scale(2);">
<i class="nopaque-icons service-color darken service-icon" data-service="nlp" style="font-size: 2.5rem;"></i>
<a href="{{ url_for('services.service', service='spacy-nlp') }}" class="btn-floating btn-large waves-effect waves-light" style="transform: scale(2);">
<i class="nopaque-icons service-color darken service-icon" data-service="spacy-nlp" style="font-size: 2.5rem;"></i>
</a>
<br><br>
<p class="service-color-text darken" data-service="nlp"><b>Natural Language Processing</b></p>
<p class="service-color-text darken" data-service="spacy-nlp"><b>Natural Language Processing</b></p>
<p class="light">By means of computational linguistic data processing (tokenization, lemmatization, part-of-speech tagging and named-entity recognition) nopaque extracts additional information from your text.</p>
<a href="{{ url_for('services.service', service='nlp') }}" class="waves-effect waves-light btn service-color darken" data-service="nlp">Create Job</a>
<a href="{{ url_for('services.service', service='spacy-nlp') }}" class="waves-effect waves-light btn service-color darken" data-service="spacy-nlp">Create Job</a>
</div>
</div>
</div>

6
app/templates/main/index.html.j2
View File

@ -84,11 +84,11 @@
<p class="light">Digital copies of text based research data (books, letters, etc.) often comprise various files and formats. nopaque converts and merges those files to facilitate further processing and the application of other services.</p>
</div>
<div class="col s12 m6 l3 center-align">
<a href="{{ url_for('services.service', service='ocr') }}" class="btn-floating btn-large btn-scale-x2 waves-effect waves-light">
<i class="nopaque-icons service-color darken service-icon" data-service="ocr"></i>
<a href="{{ url_for('services.service', service='tesseract-ocr') }}" class="btn-floating btn-large btn-scale-x2 waves-effect waves-light">
<i class="nopaque-icons service-color darken service-icon" data-service="tesseract-ocr"></i>
</a>
<br><br>
<p class="service-color-text text-darken" data-service="ocr"><b>Optical Character Recognition</b></p>
<p class="service-color-text text-darken" data-service="tesseract-ocr"><b>Optical Character Recognition</b></p>
<p class="light">nopaque converts your image data – like photos or scans – into text data through OCR making it machine readable. This step enables you to proceed with further computational analysis of your documents.</p>
</div>
<div class="col s12 m6 l3 center-align">

12
app/templates/services/nlp.html.j2 → app/templates/services/spacy_nlp.html.j2
View File

@ -2,7 +2,7 @@
{% from "services/_breadcrumbs.html.j2" import breadcrumbs with context %}
{% import "materialize/wtf.html.j2" as wtf %}
{% block main_attribs %} class="service-scheme" data-service="nlp"{% endblock main_attribs %}
{% block main_attribs %} class="service-scheme" data-service="spacy-nlp"{% endblock main_attribs %}
{% block page_content %}
<div class="container">
@ -16,13 +16,13 @@
<p class="hide-on-small-only">&nbsp;</p>
<p class="hide-on-small-only">&nbsp;</p>
<a class="btn-floating btn-large btn-scale-x2 waves-effect waves-light">
<i class="nopaque-icons service-color darken service-icon" data-service="nlp"></i>
<i class="nopaque-icons service-color darken service-icon" data-service="spacy-nlp"></i>
</a>
</div>
</div>
<div class="col s12 m9 pull-m3">
<div class="card service-color-border border-darken" data-service="nlp" style="border-top: 10px solid;">
<div class="card service-color-border border-darken" data-service="spacy-nlp" style="border-top: 10px solid;">
<div class="card-content">
<div class="row">
<div class="col s12 m6">
@ -71,7 +71,7 @@
{{ wtf.render_field(form.files, accept='text/plain', placeholder='Choose your .txt files') }}
</div>
<div class="col s12 l4">
{{ wtf.render_field(form.language, material_icon='language') }}
{{ wtf.render_field(form.model, material_icon='language') }}
</div>
<div class="col s12 l3">
{{ wtf.render_field(form.version, material_icon='apps') }}
@ -80,13 +80,13 @@
<span class="card-title">Preprocessing</span>
</div>
<div class="col s9">
<p>{{ form.check_encoding.label.text }}</p>
<p>{{ form.encoding_detection.label.text }}</p>
<p class="light">If the input files are not created with the nopaque OCR service or you do not know if your text files are UTF-8 encoded, check this switch. We will try to automatically determine the right encoding for your texts to process them.</p>
</div>
<div class="col s3 right-align">
<div class="switch">
<label>
{{ form.check_encoding() }}
{{ form.encoding_detection() }}
<span class="lever"></span>
</label>
</div>

12
app/templates/services/ocr.html.j2 → app/templates/services/tesseract_ocr.html.j2
View File

@ -2,7 +2,7 @@
{% from "services/_breadcrumbs.html.j2" import breadcrumbs with context %}
{% import "materialize/wtf.html.j2" as wtf %}
{% block main_attribs %} class="service-scheme" data-service="ocr"{% endblock main_attribs %}
{% block main_attribs %} class="service-scheme" data-service="tesseract-ocr"{% endblock main_attribs %}
{% block page_content %}
<div class="container">
@ -16,13 +16,13 @@
<p class="hide-on-small-only">&nbsp;</p>
<p class="hide-on-small-only">&nbsp;</p>
<a class="btn-floating btn-large btn-scale-x2 waves-effect waves-light">
<i class="nopaque-icons service-color darken service-icon" data-service="ocr"></i>
<i class="nopaque-icons service-color darken service-icon" data-service="tesseract-ocr"></i>
</a>
</div>
</div>
<div class="col s12 m9 pull-m3">
<div class="card service-color-border border-darken" data-service="ocr" style="border-top: 10px solid;">
<div class="card service-color-border border-darken" data-service="tesseract-ocr" style="border-top: 10px solid;">
<div class="card-content">
<div class="row">
<div class="col s12">
@ -50,10 +50,10 @@
{{ wtf.render_field(form.description, data_length='255', material_icon='description') }}
</div>
<div class="col s12 l5">
{{ wtf.render_field(form.files, accept='application/pdf', color=ocr_color_darken, placeholder='Choose your .pdf files') }}
{{ wtf.render_field(form.files, accept='application/pdf', placeholder='Choose your .pdf files') }}
</div>
<div class="col s12 l4">
{{ wtf.render_field(form.language, material_icon='language') }}
{{ wtf.render_field(form.model, material_icon='language') }}
</div>
<div class="col s12 l3">
{{ wtf.render_field(form.version, material_icon='apps') }}
@ -127,7 +127,7 @@
</div>
</div>
<div class="card-action right-align">
{{ wtf.render_field(form.submit, color=ocr_color_darken, material_icon='send') }}
{{ wtf.render_field(form.submit, material_icon='send') }}
</div>
</form>
</div>