Merge pull request #13 from fabfab1/develop

Develop

Author: Forni B

EnCAB/EnCAB.py

@@ -1,8 +1,6 @@
 # EnCAB
-> Work in progress
-
-Python program to update static website with indexes and algorithms.
 
+Python program to update static HTML website with algorithms and index imported from XML data.
 
 
 ## Getting started
@@ -26,26 +24,32 @@ Press ENTER to confirm configuration and update HTML files.
 
 ### Built With
 
-Python 3, with Jinja2 (for templating) and BeautifulSoup (for editing HTML).
+Python 3, with Jinja2 (for templating), ElementTree (for parsing XML) and BeautifulSoup (for parsing HTML).
 
 
 ## Configuration
 
-Edit config file ("config.py") to change directories and preference.
-The program will access the HTML files and the algorithms data.
-The algorithms data are XML files for each algorithm.
+Edit config file "config.py" to change directories and other preferences.
 
-The website MUST contain the directories named as the different <algorithm_description>,
-each containing the different HTML files to be indexed.
+The program will read the HTML files and the algorithms data.
+It will write the HTML data in *.html files inside ```<section block="algorithm/index" sort="(name)"></section>```.
 
+```block="algorithm" sort="(name)"``` write algorithms data, insert in (name) a SORT_STRINGS (from "config.py") or XML XPath of desired item to sort
 
-## Tests
+```block="index" sort="(name)"``` write files index, insert in (name) the folder name of desired files to use for the sorted index
 
-[coming soon]
+### Data
 
-```shell
-test/test.py
-```
+Each algorithms must have its own XML file stored in ALGORITHMS_DIR with .xml or .txt extension.
+See "- algorithms codes format" for mandatory format of the codes.
+
+### HTML Templates
+
+Templates are written in Jinja2 templating language. The XML ElementTree is passed as argument.
+
+### Errors
+
+The log with the errors found are stored in the file "log.txt".
 
 
 ## Licensing

EnCAB/README.md

@@ -17,16 +17,11 @@
 TEMPLATE_INDEX = "templates/index.html"  # default: "templates/index.html"
 
 
-# Extra options
-
-# List of used tags to check for unknown tags in XML input
-KNOWN_TAGS = ["reference", "biblioref", "authorgroup"]
-
 # List of possible sort attributes for <section> with relative XML tag
-SORT_STRINGS = {'algorithm_types': 'algorithm_description/algorithm_types',
+SORT_STRINGS = {'algorithm_type': 'algorithm_description/algorithm_type',
                 'position_in_process': 'algorithm_description/position_in_process',
                 'material': 'algorithm_description/material',
-                'abbrev': 'reference'}
+                'abbrev': 'biblioref/abbrev'}
 
-# INDEXES = [..,..] folders
-# IGNORE_IF_CONTAIN = "_index"  #_files to ignore in index
+# String to select files containing it in their filename, those files will be ignored for the index
+IGNORE_IF_CONTAIN = "_index"  # default: "_index"

EnCAB/config.py

@@ -1,5 +1,3 @@
-Jinja2==2.10
-MarkupSafe==1.0
-beautifulsoup4==4.6.0
-#Flask
-#Frozen-Flask
+Jinja2
+MarkupSafe
+beautifulsoup4

EnCAB/requirements.txt

@@ -1,11 +1,15 @@
 
-{% for b, filename in blocks_data -%}
-<a href="#{{ b.find('reference').text }}">{{ b.find('reference').text|replace('_','&nbsp;') }}</a>{% if not loop.last %}&nbsp;- {% endif %}
-{% endfor %}
+{#- --- INDEX --- #}
+{%- set ns = namespace(new_sort = '') %}
+{% for b, filename in blocks_data -%}{% if b.find(sort).text.lower() != ns.new_sort.lower() %}{% set ns.new_sort = b.find(sort).text %}
+{% if ns.new_sort %}{% if not loop.first %} - {% endif %}<a href="#{{ ns.new_sort.lower() }}">{{ ns.new_sort|replace('_','&nbsp;') }}</a>{% endif %}
+{%- endif %}{% endfor %}
+{% set ns.new_sort = '' %}
 
 <br><br><br>
 
 {% for b, filename in blocks_data %}
+{% if b.find(sort).text.lower() != ns.new_sort.lower() %}{% set ns.new_sort = b.find(sort).text %}<a name="{{ ns.new_sort.lower() }}"></a>{% endif %}
 <a name="{{ b.find('reference').text }}"></a>
 <b>{{ b.find('reference').text|replace('_','&nbsp;') }}</b>
 <table class="data">
@@ -42,18 +46,18 @@
         {% endif %}</td>
     </tr>
     <tr>
-        <td>Source info:</td><td>{% if b.find('biblioref/authorgroup/author').text %}<a href="../bibliography/bibliography.html#{{(b.find('biblioref/authorgroup/author/surname').text or '').strip('.,')|replace(' ','')}}{{(b.find('biblioref/authorgroup/author/firstname').text or '').strip('.,')|replace(' ','')}}">{{ b.find('biblioref/abbrev').text|replace('_',' ') }}</a>{% else %}{{ (b.find('biblioref/abbrev').text|replace('_',' ')) or '' }}{% endif %}
+        <td>Source info:</td><td>{% if b.find('biblioref/authorgroup/author').text %}<a href="../bibliography/bibliography.html#{{(b.find('biblioref/authorgroup/author/surname').text or '').strip('.,')|replace(' ','')}}{{(b.find('biblioref/authorgroup/author/firstname').text or '').strip('.,')|replace(' ','')}}">{{ b.find('biblioref/abbrev').text|replace('_',' ') }}</a>{% else %}{{ (b.find('biblioref/abbrev').text or '')|replace('_',' ') }}{% endif %}
         {%- if b.find('biblioref/pagenums').text %}, {{ b.find('biblioref/pagenums').text }}{% endif %}</td>
-        <td>Also cited in:</td><td>{% if b.find('biblioref/authorgroup/author2').text %}<a href="../bibliography/bibliography.html#{{(b.find('biblioref/authorgroup/author2/surname').text or '').strip('.,')|replace(' ','')}}{{(b.find('biblioref/authorgroup/author2/firstname').text or '').strip('.,')|replace(' ','')}}">{{ b.find('biblioref/abbrev2').text|replace('_',' ') }}</a>{% else %}{{ (b.find('biblioref/abbrev2').text|replace('_',' ')) or '' }}{% endif %}
+        <td>Also cited in:</td><td>{% if b.find('biblioref/authorgroup/author2').text %}<a href="../bibliography/bibliography.html#{{(b.find('biblioref/authorgroup/author2/surname').text or '').strip('.,')|replace(' ','')}}{{(b.find('biblioref/authorgroup/author2/firstname').text or '').strip('.,')|replace(' ','')}}">{{ b.find('biblioref/abbrev2').text|replace('_',' ') }}</a>{% else %}{{ (b.find('biblioref/abbrev2').text or '')|replace('_',' ') }}{% endif %}
         {%- if b.find('biblioref/pagenums2').text %}, {{ b.find('biblioref/pagenums').text }}{% endif %}</td>
     </tr>
     <tr>
-        <td>Algorithm type:</td><td>{% if b.find('algorithm_description/algorithm_type').text %}<a href="../algorithm_type/{{b.find('algorithm_description/algorithm_type').text|replace(' ','_')|lower}}.html">{{ b.find('algorithm_description/algorithm_type').text }}</a>{% endif %}</td>
-        <td>Position in process:</td><td>{% if b.find('algorithm_description/position_in_process').text %}<a href="../position_in_process/{{b.find('algorithm_description/position_in_process').text|replace(' ','_')|lower}}.html">{{ b.find('algorithm_description/position_in_process').text }}</a>{% endif %}</td>
+        <td>Algorithm type:</td><td>{% if b.find('algorithm_description/algorithm_type').text %}<a href="../algorithm_type/{{b.find('algorithm_description/algorithm_type').text|replace(' ','_')|lower}}.html">{{ b.find('algorithm_description/algorithm_type').text|title }}</a>{% endif %}</td>
+        <td>Position in process:</td><td>{% if b.find('algorithm_description/position_in_process').text %}<a href="../position_in_process/{{b.find('algorithm_description/position_in_process').text|replace(' ','_')|lower}}.html">{{ b.find('algorithm_description/position_in_process').text|title }}</a>{% endif %}</td>
     </tr>
     <tr>
-        <td>Material:</td><td>{% if b.find('algorithm_description/material').text %}<a href="../material/{{b.find('algorithm_description/material').text|replace(' ','_')|lower}}.html">{{ b.find('algorithm_description/material').text }}</a>{% endif %}</td>
-        <td>Source type:</td><td>{% if b.find('algorithm_description/source_type').text %}<a href="../source_type/{{b.find('algorithm_description/source_type').text|replace(' ','_')|lower}}.html">{{ b.find('algorithm_description/source_type').text }}</a>{% endif %}</td>
+        <td>Material:</td><td>{% if b.find('algorithm_description/material').text %}<a href="../material/{{b.find('algorithm_description/material').text|replace(' ','_')|lower}}.html">{{ b.find('algorithm_description/material').text|title }}</a>{% endif %}</td>
+        <td>Source type:</td><td>{% if b.find('algorithm_description/source_type').text %}<a href="../source_type/{{b.find('algorithm_description/source_type').text|replace(' ','_')|lower}}.html">{{ b.find('algorithm_description/source_type').text|title }}</a>{% endif %}</td>
     </tr>
     <tr>
         <td>Source chronology:</td><td>{% if b.find('algorithm_description/source_chronology').text %}<a href="../source_chronology/{{b.find('algorithm_description/source_chronology').text|replace(' ','_')|lower}}.html">{{ b.find('algorithm_description/source_chronology').text }}</a>{% endif %}</td>

EnCAB/templates/algorithm.html

@@ -1,20 +1,13 @@
 List of things still to do in EnCAB Program:
+--------------------------------------------
 
 
-
-- check Aurence <op>
-
-
-The HTML files where the algorithms are placed should have links to anchors for the different categories; example, at the top of 'Algorithms by Material' instead of links to the individual algorithms (Abrans 1994_47_1 etc) there should be links to the materials, so 'earth', 'mudbrick', 'pise'', 'plaster' etc. The same for the algorithm_type.html and the algorithm_position_in_process.html. The algorithm_bibliography.html would instead be by author_year, so Abrams 1994.
-
-update Readme file
-
 write programming page
 
 write Bernardo bio page
 
+favicon.ico ?
 
-----------
-
-create a CSV data dump from all the input files used (also the ones with errors) with the XML tags as headers. Filename should be "EnCAB_input_xyz.csv" where xyz is the date (year month day format) and time. the seperator should be a tab character (the error trapping should give an error if there is a tab used in the input, and should replace that character with 5 spaces when sending to the CSV file)
 
+CSV data dump from all the input files used (also the ones with errors) with the XML tags as headers. Filename should be "EnCAB_input_xyz.csv" where xyz is the date (year month day format) and time.
+ the separator should be a tab character (the error trapping should give an error if there is a tab used in the input, and should replace that character with 4 spaces when sending to the CSV file)

EnCAB/to-do programming.txt

@@ -27,8 +27,8 @@ <h4> Index: </h4>
 <a href="tools.html">tools</a> &nbsp;
 <a href="transport.html">transport</a> &nbsp;
 <a href="wall_building.html">wall&nbsp;building</a> &nbsp;
-    </section>
+</section>
     <h4><a name="al_type">Algorithm Type</a></h4>
     <p>Algorithm Type</p>
   </body>
-</html>
+</html>