mirror of
https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque.git
synced 2025-11-03 20:02:47 +00:00
Add a manual page
This commit is contained in:
Patrick Jentsch
@@ -33,6 +33,11 @@ def dashboard():
|
||||
return render_template('main/dashboard.html.j2', title='Dashboard')
|
||||
|
||||
|
||||
@bp.route('/user_manual')
|
||||
def user_manual():
|
||||
return render_template('main/user_manual.html.j2', title='User manual')
|
||||
|
||||
|
||||
@bp.route('/news')
|
||||
def news():
|
||||
return render_template('main/news.html.j2', title='News')
|
||||
|
||||
BIN
app/static/images/manual/add-corpus-file.png
Normal file
BIN
app/static/images/manual/add-corpus-file.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 91 KiB |
BIN
app/static/images/manual/corpus.png
Normal file
BIN
app/static/images/manual/corpus.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 125 KiB |
BIN
app/static/images/manual/create-a-corpus.png
Normal file
BIN
app/static/images/manual/create-a-corpus.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 77 KiB |
BIN
app/static/images/manual/dashboard.png
Normal file
BIN
app/static/images/manual/dashboard.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 155 KiB |
BIN
app/static/images/manual/job.png
Normal file
BIN
app/static/images/manual/job.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 122 KiB |
BIN
app/static/images/manual/registration-and-log-in.png
Normal file
BIN
app/static/images/manual/registration-and-log-in.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1018 KiB |
BIN
app/static/images/manual/services.png
Normal file
BIN
app/static/images/manual/services.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 309 KiB |
@@ -27,6 +27,7 @@
|
||||
</div>
|
||||
|
||||
<ul class="dropdown-content" id="nav-more-dropdown">
|
||||
<li><a href="{{ url_for('main.user_manual') }}"><i class="material-icons left">help</i>Manual</a></li>
|
||||
{% if current_user.is_authenticated %}
|
||||
<li><a href="{{ url_for('settings.index') }}"><i class="material-icons left">settings</i>Settings</a></li>
|
||||
<li class="divider" tabindex="-1"></li>
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
</li>
|
||||
<li><a href="{{ url_for('main.index') }}">nopaque</a></li>
|
||||
<li><a href="{{ url_for('main.news') }}"><i class="material-icons left">email</i>News</a></li>
|
||||
<li><a href="#"><i class="material-icons">linear_scale</i>Workflow</a></li>
|
||||
<li><a href="{{ url_for('main.user_manual') }}"><i class="material-icons">help</i>Manual</a></li>
|
||||
<li><a href="{{ url_for('main.dashboard') }}"><i class="material-icons">dashboard</i>Dashboard</a></li>
|
||||
<li><a href="{{ url_for('main.dashboard', _anchor='corpora') }}" style="padding-left: 47px;"><i class="nopaque-icons">I</i>My Corpora</a></li>
|
||||
<li><a href="{{ url_for('main.dashboard', _anchor='jobs') }}" style="padding-left: 47px;"><i class="nopaque-icons">J</i>My Jobs</a></li>
|
||||
|
||||
@@ -6,9 +6,12 @@
|
||||
<div class="row">
|
||||
<div class="input-field col s12 m9">
|
||||
<i class="material-icons prefix">search</i>
|
||||
<input class="validate corpus-analysis-action" id="concordance-extension-form-query" name="query" type="text" required pattern=".*\S+.*"></input>
|
||||
<input class="validate corpus-analysis-action" id="concordance-extension-form-query" name="query" type="text" required pattern=".*\S+.*" placeholder="<ent_type="PERSON"> []* </ent_type> []* [simple_pos="VERB"] :: match.text_publishing_year="1991";"></input>
|
||||
<label for="concordance-extension-form-query">Query</label>
|
||||
<span class="error-color-text helper-text hide" id="concordance-extension-error"></span>
|
||||
<a class="modal-trigger" href="#cql-tutorial-modal" style="margin-left: 40px;"><i class="material-icons" style="font-size: inherit;">help</i> Corpus Query Language tutorial</a>
|
||||
<span> | </span>
|
||||
<a class="modal-trigger" href="#tagsets-modal"><i class="material-icons" style="font-size: inherit;">info</i> Tagsets</a>
|
||||
</div>
|
||||
<div class="input-field col s12 m3">
|
||||
<i class="material-icons prefix">arrow_forward</i>
|
||||
|
||||
@@ -53,6 +53,198 @@
|
||||
<p class="error-color-text hide" id="corpus-analysis-app-init-error"></p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="modal" id="cql-tutorial-modal">
|
||||
<div class="modal-content">
|
||||
{% with headline_num=4 %}
|
||||
{% include "main/manual/_08_cqp_query_language.html.j2" %}
|
||||
{% endwith %}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="modal" id="tagsets-modal">
|
||||
<div class="modal-content">
|
||||
<h4>Tagsets</h4>
|
||||
<ul class="tabs">
|
||||
<li class="tab"><a class="active" href="#simple_pos-tagset">simple_pos</a></li>
|
||||
<li class="tab"><a href="#english-ent_type-tagset">English ent_type</a></li>
|
||||
<li class="tab"><a href="#english-pos-tagset">English pos</a></li>
|
||||
<li class="tab"><a href="#german-ent_type-tagset">German ent_type</a></li>
|
||||
<li class="tab"><a href="#german-pos-tagset">German pos</a></li>
|
||||
</ul>
|
||||
|
||||
<div id="simple_pos-tagset">
|
||||
<h5>simple_pos tagset</h5>
|
||||
<ul>
|
||||
<li>ADJ: adjective</li>
|
||||
<li>ADP: adposition</li>
|
||||
<li>ADV: adverb</li>
|
||||
<li>AUX: auxiliary verb</li>
|
||||
<li>CONJ: coordinating conjunction</li>
|
||||
<li>DET: determiner</li>
|
||||
<li>INTJ: interjection</li>
|
||||
<li>NOUN: noun</li>
|
||||
<li>NUM: numeral</li>
|
||||
<li>PART: particle</li>
|
||||
<li>PRON: pronoun</li>
|
||||
<li>PROPN: proper noun</li>
|
||||
<li>PUNCT: punctuation</li>
|
||||
<li>SCONJ: subordinating conjunction</li>
|
||||
<li>SYM: symbol</li>
|
||||
<li>VERB: verb</li>
|
||||
<li>X: other</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div id="english-ent_type-tagset">
|
||||
<h5>English ent_type tagset</h5>
|
||||
<ul>
|
||||
<li>CARDINAL: Numerals that do not fall under another type</li>
|
||||
<li>DATE: Absolute or relative dates or periods</li>
|
||||
<li>EVENT: Named hurricanes, battles, wars, sports events, etc.</li>
|
||||
<li>FAC: Buildings, airports, highways, bridges, etc.</li>
|
||||
<li>GPE: Countries, cities, states</li>
|
||||
<li>LANGUAGE: Any named language</li>
|
||||
<li>LAW: Named documents made into laws.</li>
|
||||
<li>LOC: Non-GPE locations, mountain ranges, bodies of water</li>
|
||||
<li>MONEY: Monetary values, including unit</li>
|
||||
<li>NORP: Nationalities or religious or political groups</li>
|
||||
<li>ORDINAL: "first" "second" etc.</li>
|
||||
<li>ORG: Companies, agencies, institutions, etc.</li>
|
||||
<li>PERCENT: Percentage, including "%"</li>
|
||||
<li>PERSON: People, including fictional</li>
|
||||
<li>PRODUCT: Objects, vehicles, foods, etc. (not services)</li>
|
||||
<li>QUANTITY: Measurements, as of weight or distance</li>
|
||||
<li>TIME: Times smaller than a day</li>
|
||||
<li>WORK_OF_ART: Titles of books, songs, etc.</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div id="english-pos-tagset">
|
||||
<h5>English pos tagset</h5>
|
||||
<ul>
|
||||
<li>ADD: email</li>
|
||||
<li>AFX: affix</li>
|
||||
<li>CC: conjunction, coordinating</li>
|
||||
<li>CD: cardinal number</li>
|
||||
<li>DT: determiner</li>
|
||||
<li>EX: existential there</li>
|
||||
<li>FW: foreign word</li>
|
||||
<li>HYPH: punctuation mark, hyphen</li>
|
||||
<li>IN: conjunction, subordinating or preposition</li>
|
||||
<li>JJ: adjective</li>
|
||||
<li>JJR: adjective, comparative</li>
|
||||
<li>JJS: adjective, superlative</li>
|
||||
<li>LS: list item marker</li>
|
||||
<li>MD: verb, modal auxiliary</li>
|
||||
<li>NFP: superfluous punctuation</li>
|
||||
<li>NN: noun, singular or mass</li>
|
||||
<li>NNP: noun, proper singular</li>
|
||||
<li>NNPS: noun, proper plural</li>
|
||||
<li>NNS: noun, plural</li>
|
||||
<li>PDT: predeterminer</li>
|
||||
<li>POS: possessive ending</li>
|
||||
<li>PRP: pronoun, personal</li>
|
||||
<li>PRP$: pronoun, possessive RB: adverb</li>
|
||||
<li>RBR: adverb, comparative</li>
|
||||
<li>RBS: adverb, superlative</li>
|
||||
<li>RP: adverb, particle</li>
|
||||
<li>SYM: symbol</li>
|
||||
<li>TO: infinitival "to"</li>
|
||||
<li>UH: interjection</li>
|
||||
<li>VB: verb, base form</li>
|
||||
<li>VBD: verb, past tense</li>
|
||||
<li>VBG: verb, gerund or present participle</li>
|
||||
<li>VBN: verb, past participle</li>
|
||||
<li>VBP: verb, non-3rd person singular present</li>
|
||||
<li>VBZ: verb, 3rd person singular present</li>
|
||||
<li>WDT: wh-determiner</li>
|
||||
<li>WP: wh-pronoun, personal</li>
|
||||
<li>WP$: wh-pronoun, possessive</li>
|
||||
<li>WRB: wh-adverb</li>
|
||||
<li>XX: unknown</li>
|
||||
<li>``: opening quotation mark</li>
|
||||
<li>$: symbol, currency</li>
|
||||
<li>'': closing quotation mark</li>
|
||||
<li>: punctuation mark, comma</li>
|
||||
<li>-LRB-: left round bracket</li>
|
||||
<li>-RRB-: right round bracket</li>
|
||||
<li>.: punctuation mark, sentence closer</li>
|
||||
<li>:: punctuation mark, colon or ellipsis</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div id="german-ent_type-tagset">
|
||||
<h5>German ent_type tagset</h5>
|
||||
<ul>
|
||||
<li>LOC: Non-GPE locations, mountain ranges, bodies of water</li>
|
||||
<li>MISC: Miscellaneous entities, e.g. events, nationalities, products or works of art</li>
|
||||
<li>ORG: Companies, agencies, institutions, etc.</li>
|
||||
<li>PER: Named person or family.</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div id="german-pos-tagset">
|
||||
<h5>German pos tagset</h5>
|
||||
<ul>
|
||||
<li>ADJA: adjective, attributive</li>
|
||||
<li>ADJD: adjective, adverbial or predicative</li>
|
||||
<li>ADV: adverb</li>
|
||||
<li>APPO: postposition</li>
|
||||
<li>APPR: preposition; circumposition left</li>
|
||||
<li>APPRART: preposition with article</li>
|
||||
<li>APZR: circumposition right</li>
|
||||
<li>ART: definite or indefinite article</li>
|
||||
<li>CARD: cardinal number</li>
|
||||
<li>FM: foreign language material</li>
|
||||
<li>ITJ: interjection</li>
|
||||
<li>KOKOM: comparative conjunction</li>
|
||||
<li>KON: coordinate conjunction</li>
|
||||
<li>KOUI: subordinate conjunction with \zu\ and infinitive</li>
|
||||
<li>KOUS: subordinate conjunction with sentence</li>
|
||||
<li>NE: proper noun</li>
|
||||
<li>NN: noun, singular or mass</li>
|
||||
<li>NNE: proper noun</li>
|
||||
<li>PDAT: attributive demonstrative pronoun</li>
|
||||
<li>PDS: substituting demonstrative pronoun</li>
|
||||
<li>PIAT: attributive indefinite pronoun without determiner</li>
|
||||
<li>PIS: substituting indefinite pronoun</li>
|
||||
<li>PPER: non-reflexive personal pronoun</li>
|
||||
<li>PPOSAT: attributive possessive pronoun</li>
|
||||
<li>PPOSS: substituting possessive pronoun</li>
|
||||
<li>PRELAT: attributive relative pronoun</li>
|
||||
<li>PRELS: substituting relative pronoun</li>
|
||||
<li>PRF: reflexive personal pronoun</li>
|
||||
<li>PROAV: pronominal adverb</li>
|
||||
<li>PTKA: particle with adjective or adverb</li>
|
||||
<li>PTKANT: answer particle</li>
|
||||
<li>PTKNEG: negative particle</li>
|
||||
<li>PTKVZ: separable verbal particle</li>
|
||||
<li>PTKZU: "zu" before infinitive</li>
|
||||
<li>PWAT: attributive interrogative pronoun</li>
|
||||
<li>PWAV: adverbial interrogative or relative pronoun</li>
|
||||
<li>PWS: substituting interrogative pronoun</li>
|
||||
<li>TRUNC: word remnant</li>
|
||||
<li>VAFIN: finite verb, auxiliary</li>
|
||||
<li>VAIMP: imperative, auxiliary</li>
|
||||
<li>VAINF: infinitive, auxiliary</li>
|
||||
<li>VAPP: perfect participle, auxiliary</li>
|
||||
<li>VMFIN: finite verb, modal</li>
|
||||
<li>VMINF: infinitive, modal</li>
|
||||
<li>VMPP: perfect participle, modal</li>
|
||||
<li>VVFIN: finite verb, full</li>
|
||||
<li>VVIMP: imperative, full</li>
|
||||
<li>VVINF: infinitive, full</li>
|
||||
<li>VVIZU: infinitive with "zu" full</li>
|
||||
<li>VVPP: perfect participle, full</li>
|
||||
<li>XY: non-word containing non-letter</li>
|
||||
<li>$(: other sentence-internal punctuation mark</li>
|
||||
<li>$,: comma</li>
|
||||
<li>$.: sentence-final punctuation mark</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
{% endblock modals %}
|
||||
|
||||
{% block scripts %}
|
||||
|
||||
9
app/templates/main/manual/_01_introduction.html.j2
Normal file
9
app/templates/main/manual/_01_introduction.html.j2
Normal file
@@ -0,0 +1,9 @@
|
||||
<h2>Introduction</h2>
|
||||
<p>
|
||||
nopaque is a web-based digital working environment. It implements a
|
||||
workflow based on the research process in the humanities and supports its
|
||||
users in processing their data in order to subsequently apply digital
|
||||
analysis methods to them. All processes are implemented in a specially
|
||||
provided cloud environment with established open source software. This
|
||||
always ensures that no personal data of the users is disclosed.
|
||||
</p>
|
||||
@@ -0,0 +1,18 @@
|
||||
<h2>Registration and Log in</h2>
|
||||
<div class="row">
|
||||
<div class="col s12 m4">
|
||||
<img alt="Registration and Log in" class="materialboxed responsive-img" src="{{ url_for('static', filename='images/manual/registration-and-log-in.png') }}">
|
||||
</div>
|
||||
<div class="col s12 m8">
|
||||
<p>
|
||||
Before you can start using the web platform, you need to create a user
|
||||
account. This requires only a few details: just a user name, an e-mail
|
||||
address and a password are needed. In order to register yourself, fill out
|
||||
the form on the <a href="{{ url_for('auth.register') }}">registration page</a>. After successful registration, the
|
||||
created account must be verified. To do this, follow the instructions
|
||||
given in the automatically sent e-mail. Afterwards, you can log in as
|
||||
usual with your username/email address and password in the log-in form
|
||||
located next to the registration button.
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
46
app/templates/main/manual/_03_dashboard.html.j2
Normal file
46
app/templates/main/manual/_03_dashboard.html.j2
Normal file
@@ -0,0 +1,46 @@
|
||||
<h2>Dashboard</h2>
|
||||
<div class="row">
|
||||
<div class="col s12 m4">
|
||||
<img alt="Dashboard" class="materialboxed responsive-img" src="{{ url_for('static', filename='images/manual/dashboard.png') }}">
|
||||
</div>
|
||||
<div class="col s12 m8">
|
||||
<p>
|
||||
The <a href="{{ url_for('main.dashboard') }}">dashboard</a> provides a central overview of all resources assigned to the
|
||||
user. These are <a href="{{ url_for('main.dashboard', _anchor='corpora') }}">corpora</a> and created <a href="{{ url_for('main.dashboard', _anchor='jobs') }}">jobs</a>. Corpora are freely composable
|
||||
annotated text collections and jobs are the initiated file processing
|
||||
procedures. Both the job and the corpus listings can be searched using
|
||||
the search field displayed above them.
|
||||
</p>
|
||||
</div>
|
||||
<div class="col s12"> </div>
|
||||
<div class="col s12 m6">
|
||||
<div class="card">
|
||||
<div class="card-content">
|
||||
<span class="card-title"><i class="nopaque-icons">I</i> Corpus</span>
|
||||
<p>
|
||||
A corpus is a collection of texts that can be analyzed using the
|
||||
Corpus Analysis service. All texts must be in the verticalized text
|
||||
file format, which can be obtained via the Natrual Language
|
||||
Processing service. It contains, in addition to the actual text,
|
||||
further annotations that are searchable in combination with optional
|
||||
addable metadata during your analysis.
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="col s12 m6">
|
||||
<div class="card">
|
||||
<div class="card-content">
|
||||
<span class="card-title"><i class="nopaque-icons">J</i> Job</span>
|
||||
<p>
|
||||
A job is a construct that represents the execution of a service.
|
||||
It stores input files, output files, processing status, and options
|
||||
selected during creation. After submitting a job, you get redirected
|
||||
to a job overview page. This can be accessed again via the job list
|
||||
on the dashboard. Jobs will be deleted three months after creation,
|
||||
so we encourage you to download the results after a job is completed.
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
52
app/templates/main/manual/_06_services.html.j2
Normal file
52
app/templates/main/manual/_06_services.html.j2
Normal file
@@ -0,0 +1,52 @@
|
||||
<h2>Services</h2>
|
||||
<div class="row">
|
||||
<div class="col s12 m4">
|
||||
<img alt="Services" class="materialboxed responsive-img" src="{{ url_for('static', filename='images/manual/services.png') }}">
|
||||
</div>
|
||||
<div class="col s12 m8">
|
||||
<p>
|
||||
nopaque was designed from the ground up to be modular. This modularity
|
||||
means that the offered workflow provides variable entry and exit points,
|
||||
so that different starting points and goals can be flexibly addressed.
|
||||
Each of these modules are implemented in a self-contained service, each of
|
||||
which represents a step in the workflow. The services are coordinated in
|
||||
such a way that they can be used consecutively. The order can either be
|
||||
taken from the listing of the services in the left sidebar or from the
|
||||
roadmap (accessible via the pink compass in the upper right corner). All
|
||||
services are versioned, so the data generated with nopaque is always
|
||||
reproducible.
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<h3>File Setup</h3>
|
||||
<p>
|
||||
The <a href="{{ url_for('services.file_setup_pipeline') }}">File Setup Service</a> bundles image data, such as scans and photos,
|
||||
together in a handy PDF file. To use this service, use the job form to
|
||||
select the images to be bundled, choose the desired service version, and
|
||||
specify a title and description. Please note that the service sorts the
|
||||
images into the resulting PDF file based on the file names. So naming the
|
||||
images correctly is of great importance. It has proven to be a good practice
|
||||
to name the files according to the following scheme:
|
||||
page-01.png, page-02.jpg, page-03.tiff, etc. In general, you can assume
|
||||
that the images will be sorted in the order in which the file explorer of
|
||||
your operating system lists them when you view the files in a folder
|
||||
sorted in ascending order by file name.
|
||||
</p>
|
||||
|
||||
<h3>Optical Character Recognition (OCR)</h3>
|
||||
<p>Comming soon...</p>
|
||||
|
||||
<h3>Handwritten Text Recognition (HTR)</h3>
|
||||
<p>Comming soon...</p>
|
||||
|
||||
<h3>Natural Language Processing (NLP)</h3>
|
||||
<p>Comming soon...</p>
|
||||
|
||||
<h3>Corpus Analysis</h3>
|
||||
<p>
|
||||
With the corpus analysis service, it is possible to create a text corpus
|
||||
and then explore it in an analysis session. The analysis session is realized
|
||||
on the server side by the Open Corpus Workbench software, which enables
|
||||
efficient and complex searches with the help of the CQP Query Language.
|
||||
</p>
|
||||
@@ -0,0 +1,47 @@
|
||||
<h2>A closer look at the Corpus Analysis</h2>
|
||||
<h3>Create a corpus</h3>
|
||||
<div class="row">
|
||||
<div class="col s12 m4">
|
||||
<img alt="Create a Corpus" class="materialboxed responsive-img" src="{{ url_for('static', filename='images/manual/create-a-corpus.png') }}">
|
||||
</div>
|
||||
<div class="col s12 m8">
|
||||
<p>
|
||||
To <a href="{{ url_for('corpora.add_corpus') }}">create a corpus</a>, you
|
||||
can use the "New Corpus" button, which can be found on both, the Corpus
|
||||
Analysis Service page and the Dashboard below the corpus list. Fill in the input
|
||||
mask to Create a corpus. After you have completed the input mask, you will
|
||||
be automatically taken to the corpus overview page (which can be called up
|
||||
again via the corpus lists) of your new and accordingly still empty corpus.
|
||||
</p>
|
||||
</div>
|
||||
<div class="col s12"> </div>
|
||||
<div class="col s12 m4">
|
||||
<img alt="Create a Corpus" class="materialboxed responsive-img" src="{{ url_for('static', filename='images/manual/add-corpus-file.png') }}">
|
||||
</div>
|
||||
<div class="col s12 m8">
|
||||
<p>
|
||||
Now you can add texts in vrt format (results of the NLP service) to your new
|
||||
corpus. To do this, use the "Add Corpus File" button and fill in the form
|
||||
that appears. You will get the possibility to add metadata to each text.
|
||||
After you have added all the desired texts to the corpus, the corpus must be
|
||||
prepared for the analysis, this process can be initiated by clicking on the
|
||||
"Build" button. On the corpus overview page you can always see information
|
||||
about the current status of the corpus in the upper right corner. After the
|
||||
build process the status should be "built".
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<h3>Analyze a corpus</h3>
|
||||
<p>
|
||||
After you have created and built a corpus, it can be analyzed. To do this,
|
||||
use the button labeled Analyze. The corpus analysis currently offers two
|
||||
modules, the Reader and the Concordance module. The reader module can be
|
||||
used to read your tokenized corpus in different ways. You can select a token
|
||||
representation option, it determines the property of a token to be shown.
|
||||
You can for example read your text completly lemmatized. You can also change
|
||||
the way of how a token is displayed, by using the text style switch. The
|
||||
concordance module offers some more options regarding the context size of
|
||||
search results. If the context does not provide enough information you can
|
||||
hop into the reader module by using the lupe icon next to a match.
|
||||
</p>
|
||||
161
app/templates/main/manual/_08_cqp_query_language.html.j2
Normal file
161
app/templates/main/manual/_08_cqp_query_language.html.j2
Normal file
@@ -0,0 +1,161 @@
|
||||
<h2>CQP Query Language</h2>
|
||||
<p>Within the Corpus Query Language, a distinction is made between two types of annotations: positional attributes and structural attributes. Positional attributes refer to a token, e.g. the word "book" is assigned the part-of-speech tag "NN", the lemma "book" and the simplified part-of-speech tag "NOUN" within the token structure. Structural attributes refer to text structure-giving elements such as sentence and entity markup. For example, the markup of a sentence is represented in the background as follows:</p>
|
||||
<pre>
|
||||
<code>
|
||||
<span class="green-text"><s> structural attribute</span>
|
||||
<span class="blue-text">word pos lemma simple_pos positional attribute</span>
|
||||
<span class="green-text"><ent type="PERSON"> structural attribute</span>
|
||||
<span class="blue-text">word pos lemma simple_pos positional attribute</span>
|
||||
<span class="blue-text">word pos lemma simple_pos positional attribute</span>
|
||||
<span class="green-text"></ent> structural attribute</span>
|
||||
<span class="blue-text">word pos lemma simple_pos positional attribute</span>
|
||||
<span class="green-text"></s> structural attribute</span>
|
||||
</code>
|
||||
</pre>
|
||||
|
||||
<h3>Positional attributes</h3>
|
||||
<p>Before you can start searching for positional attributes (also called tokens), it is necessary to know what properties they contain.</p>
|
||||
<ol>
|
||||
<li><span class="blue-text"><b>word</b></span>: The string as it is also found in the original text</li>
|
||||
<li>
|
||||
<span class="blue-text"><b>pos</b></span>: A code for the word type, also called POS tag
|
||||
<ol>
|
||||
<li><span class="red-text"><b>IMPORTANT</b></span>: POS tags are language-dependent to best reflect language-specific properties.</li>
|
||||
<li>The codes (= tagsets) can be taken from the Corpus Analysis Concordance page.</li>
|
||||
</ol>
|
||||
</li>
|
||||
<li><span class="blue-text"><b>lemma</b></span>: The lemmatized representation of the word</li>
|
||||
<li>
|
||||
<span class="blue-text"><b>simple_pos</b></span>: A simplified code for the word type that covers fewer categories than the <span class="blue-text"><b>pos</b></span> property, but is the same across languages.
|
||||
<ol>
|
||||
<li>The codes (= tagsets) can be taken from the Corpus Analysis Concordance page.</li>
|
||||
</ol>
|
||||
</li>
|
||||
</ol>
|
||||
|
||||
<h4>Searching for positional attributes</h4>
|
||||
<div>
|
||||
<p>
|
||||
<b>Token with no condition on any property (also called <span class="blue-text">wildcard token</span>)</b><br>
|
||||
</p>
|
||||
<pre><code>[]; Each token matches this pattern</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p>
|
||||
<b>Token with a condition on its <span class="blue-text">word</span> property</b>
|
||||
</p>
|
||||
<pre><code>[word="begin"]; “begin”</code></pre>
|
||||
<pre><code>[word="begin" %c]; same as above but ignores case</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p>
|
||||
<b>Token with a condition on its <span class="blue-text">lemma</span> property</b>
|
||||
</p>
|
||||
<pre><code>[lemma="begin"]; “begin”, “began”, “beginning”, …</code></pre>
|
||||
<pre><code>[lemma="begin" %c]; same as above but ignores case</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p>
|
||||
<b>Token with a condition on its <span class="blue-text">simple_pos</span> property</b>
|
||||
</p>
|
||||
<pre><code>[simple_pos="VERB"]; “begin”, “began”, “beginning”, …</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p>
|
||||
<b>Token with a condition on its <span class="blue-text">pos</span> property</b>
|
||||
</p>
|
||||
<pre><code>[pos="VBG"]; “begin”, “began”, “beginning”, …</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p>
|
||||
<b>Look for words with a variable character (also called <span class="blue-text">wildcard character</span>)</b><br>
|
||||
</p>
|
||||
<pre style="margin-bottom: 0;"><code>[word="beg.n"]; “begin”, “began”, “begun”</code></pre>
|
||||
<pre style="margin-top: 0;" ><code> ^ the dot represents the wildcard character</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p><b>Token with two conditions on its properties, where both must be fulfilled (<span class="blue-text">AND</span> operation)</b></p>
|
||||
<pre style="margin-bottom: 0;"><code>[lemma="be" & simple_pos="VERB"]; Lemma “be” and simple_pos is Verb</code></pre>
|
||||
<pre style="margin-top: 0;" ><code> ^ the ampersand represents the and operation</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p><b>Token with two conditions on its properties, where at least one must be fulfilled (<span class="blue-text">OR</span> operation)</b></p>
|
||||
<pre style="margin-bottom: 0;"><code>[simple_pos="VERB" | simple_pos="ADJ"]; simple_pos VERB or simple_pos ADJ (adjective)</code></pre>
|
||||
<pre style="margin-top: 0;"><code> ^ the line represents the or operation</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p><b>Sequences</b></p>
|
||||
<pre><code>[simple_pos="NOUN"] [simple_pos="VERB"]; NOUN -> VERB</code></pre>
|
||||
<pre><code>[simple_pos="NOUN"] [] [simple_pos="VERB"]; NOUN -> wildcard token -> VERB</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p>
|
||||
<b>Incidence modifiers</b><br>
|
||||
Incidence Modifiers are special characters or patterns, that control how often a character/token that stands in front of it should occur.
|
||||
</p>
|
||||
<ol>
|
||||
<li><span class="blue-text"><b>+</b></span>: <span class="blue-text">One or more</span> occurrences of the character/token before</li>
|
||||
<li><span class="blue-text"><b>*</b></span>: <span class="blue-text">Zero or more occurrences</span> of the character/token before</li>
|
||||
<li><span class="blue-text"><b>?</b></span>: <span class="blue-text">Zero or one occurrences</span> of the character/token before</li>
|
||||
<li><span class="blue-text"><b>{n}</b></span>: <span class="blue-text">Exactly n occurrences</span> of the character/token before</li>
|
||||
<li><span class="blue-text"><b>{n,m}</b></span>: <span class="blue-text">Between n and m occurrences</span> of the character/token before</li>
|
||||
</ol>
|
||||
<pre><code>[word="beg.+"]; “begging”, “begin”, “began”, “begun”, …</code></pre>
|
||||
<pre><code>[word="beg.*"]; “beg”, “begging”, “begin”, “begun”, …</code></pre>
|
||||
<pre><code>[word="beg?"]; “be”, “beg”</code></pre>
|
||||
<pre><code>[word="beg.{2}"]; “begin”, “begun”, …</code></pre>
|
||||
<pre><code>[word="beg.{2,4}"]; “begging”, “begin”, “begun”, …</code></pre>
|
||||
<pre><code>[word="beg{2}.*"]; “begged”, “beggar”, …</code></pre>
|
||||
<pre><code>[simple_pos="NOUN"] []? [simple_pos="VERB"]; NOUN -> wildcard token (x0 or x1) -> VERB</code></pre>
|
||||
<pre><code>[simple_pos="NOUN"] []* [simple_pos="VERB"]; NOUN -> wildcard token (x0 or x1) -> VERB</code></pre>
|
||||
</div>
|
||||
<div>
|
||||
<p>
|
||||
<b>Option groups</b><br>
|
||||
Find character sequences from a list of options.
|
||||
</p>
|
||||
<pre style="margin-bottom: 0;"><code>[word="be(g|gin|gan|gun)"]; “beg”, “begin”, “began”, “begun”</code></pre>
|
||||
<pre style="margin-top: 0;" ><code> ^ ^ the braces indicate the start and end of an option group</code></pre>
|
||||
</div>
|
||||
|
||||
<h3>Structural attributes</h3>
|
||||
<p>nopaque provides several structural attributes for query. A distinction is made between attributes with and without value.</p>
|
||||
<ol>
|
||||
<li><span class="green-text"><b>s</b></span>: Annotates a sentence</li>
|
||||
<li>
|
||||
<span class="green-text"><b>ent</b></span>: Annotates an entity
|
||||
<ol>
|
||||
<li>
|
||||
<span class="green-text"><b>*ent_type</b></span>: Annotates an entity and has as value a code that identifies the type of the entity.
|
||||
<ol>
|
||||
<li>The codes (= tagsets) can be taken from the Corpus Analysis Concordance page.</li>
|
||||
</ol>
|
||||
</li>
|
||||
</ol>
|
||||
</li>
|
||||
<li>
|
||||
<span class="green-text"><b>text</b></span>: Annotates a text
|
||||
<ol>
|
||||
<li>Note that all the following attributes have the data entered during the corpus creation as value.</li>
|
||||
<li><span class="green-text"><b>*text_address</b></span></li>
|
||||
<li><span class="green-text"><b>*text_author</b></span></li>
|
||||
<li><span class="green-text"><b>*text_booktitle</b></span></li>
|
||||
<li><span class="green-text"><b>*text_chapter</b></span></li>
|
||||
<li><span class="green-text"><b>*text_editor</b></span></li>
|
||||
<li><span class="green-text"><b>*text_institution</b></span></li>
|
||||
<li><span class="green-text"><b>*text_journal</b></span></li>
|
||||
<li><span class="green-text"><b>*text_pages</b></span></li>
|
||||
<li><span class="green-text"><b>*text_publisher</b></span></li>
|
||||
<li><span class="green-text"><b>*text_publishing_year</b></span></li>
|
||||
<li><span class="green-text"><b>*text_school</b></span></li>
|
||||
<li><span class="green-text"><b>*text_title</b></span></li>
|
||||
</ol>
|
||||
</li>
|
||||
</ol>
|
||||
|
||||
<h4>Searching for structural attributes</h4>
|
||||
<pre><code><ent> [] </ent>; A one token long entity of any type</code></pre>
|
||||
<pre><code><ent_type="PERSON"> [] </ent_type>; A one token long entity of type PERSON</code></pre>
|
||||
<pre><code><ent_type="PERSON"> []* </ent_type>; Entity of any length of type PERSON</code></pre>
|
||||
<pre style="margin-bottom: 0;"><code><ent_type="PERSON"> []* </ent_type> []* [simple_pos="VERB"] :: match.text_publishing_year="1991";</code></pre>
|
||||
<pre style="margin-top: 0;"><code>Arbitrarily long entity of type PERSON -> Arbitrarily many tokens -> VERB but only within texts with publication year 1991</code></pre>
|
||||
44
app/templates/main/user_manual.html.j2
Normal file
44
app/templates/main/user_manual.html.j2
Normal file
@@ -0,0 +1,44 @@
|
||||
{% extends "base.html.j2" %}
|
||||
{% from "main/_breadcrumbs.html.j2" import breadcrumbs with context %}
|
||||
|
||||
{% block page_content %}
|
||||
<div class="container">
|
||||
<div class="row">
|
||||
<div class="col s12">
|
||||
<h1 id="title">{{ title }}</h1>
|
||||
</div>
|
||||
|
||||
<div class="col s12 m10">
|
||||
<div class="section scrollspy" id="introduction">
|
||||
{% include "main/manual/_01_introduction.html.j2" %}
|
||||
</div>
|
||||
<div class="section scrollspy" id="registration-and-log-in">
|
||||
{% include "main/manual/_02_registration_and_log_in.html.j2" %}
|
||||
</div>
|
||||
<div class="section scrollspy" id="dashboard">
|
||||
{% include "main/manual/_03_dashboard.html.j2" %}
|
||||
</div>
|
||||
<div class="section scrollspy" id="services">
|
||||
{% include "main/manual/_06_services.html.j2" %}
|
||||
</div>
|
||||
<div class="section scrollspy" id="a-closer-look-at-the-corpus-analysis">
|
||||
{% include "main/manual/_07_a_closer_look_at_the_corpus_analysis.html.j2" %}
|
||||
</div>
|
||||
<div class="section scrollspy" id="cqp-query-language">
|
||||
{% include "main/manual/_08_cqp_query_language.html.j2" %}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="col m2 hide-on-small-only">
|
||||
<ul class="section table-of-contents" style="position: fixed !important;">
|
||||
<li><a href="#introduction">Introduction</a></li>
|
||||
<li><a href="#registration-and-log-in">Registration and Log in</a></li>
|
||||
<li><a href="#dashboard">Dashboard</a></li>
|
||||
<li><a href="#services">Services</a></li>
|
||||
<li><a href="#a-closer-look-at-the-corpus-analysis">A closer look at the Corpus Analysis</a></li>
|
||||
<li><a href="#cqp-query-language">CQP Query Language</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
{% endblock page_content %}
|
||||
Reference in New Issue
Block a user