documentation

README.md

@@ -49,16 +49,32 @@ Run scripts together with `./run.sh`
     * run dry `python3 query2html.py --dry` only printing request, not executing it
     * build custom query with arguments `--conditions  --printouts  --sort  --order`
     * default query is: `[[File:+]][[Title::+]][[Part::+]][[Date::+]]|?Title|?Date|?Part|?Partof|sort=Date,Title,Part|order=asc,asc,asc`  
-    * custom query `python3 query2html.py -c '[[Date::>=1970/01/01]][[Date::<=1979/12/31]]' -p '?Title|?Date|?Part|?Partof' -s 'Date,Title,Part' -o 'asc,asc,asc'`
+    * custom queries 
+        * `python3 query2html.py --conditions '[[Date::>=1970/01/01]][[Date::<=1979/12/31]]'`
+        * `python3 query2html.py --conditions '[[Creator::~*task force*]]'`
 
-* The results, with the same Title, are stored
-    * into 1 single HTML
-    * sorted by Part
+Note: to avoid confusion or problems is better to leave the `--printouts` `--sort`  `--order` arguments as the default. 
+Otherwise document parts will start to get grouped not according to their Title, hence creating documents made from different original parts.
 
 
+## How does query2html.py work?
+
+Based on the query made:
+MW API will send back a number of Page titles that match the query conditions, 
+together with its printouts (metadata proprety::value pairs).
+
+For each Page:
+* its locally stored image is found
+* its text retrieved from MW
+* a fragment of html (`document_part_html`) is generated based on the `templates/document_part.html`
+
+All Pages that *share the same metadata's Title value*, will:
+* gather all their html fragments in `all_document_parts` 
+* render `templates/document.html` with the content of `all_document_parts`   
+* save the render template to `'static_html/DocumentTitle.html'`, 
+    
+Each of the saved documents:
+* render `templates/index.html` with the info on each document has been saved into `documentslist`  
+* resulting in `static_html/index.html`
+ 
 
-## TODO
-* remove HTML files at each new query
-* revise `def unpack_response()` so that it returns the values of all properties printed out
-* revise template so that they include the values of all properties printed out \
-and do not break on missing values

query2html.py

@@ -15,7 +15,7 @@ p.add_argument("--conditions", "-c", metavar='',
                default='[[File:+]][[Title::+]][[Part::+]][[Date::+]]',
                help='The query conditions')
 p.add_argument("--printouts", "-p", metavar='',
-               default='?Title|?Date|?Part|?Partof',
+               default='?Title|?Date|?Part|?Partof|?Creator',
                help='Selection of properties to printout')
 p.add_argument("--sort", "-s", metavar='',
                default='Date,Title,Part',
@@ -89,7 +89,8 @@ for answer in site.ask(query):
     pagetext = page.text()
     pagetext_html = pandoc(pwd=wd, content=pagetext, format_in='mediawiki', format_out='html')
     img_local = os.path.join(imgdir, img_info.get('filename'))
-    # render html for that part of the document
+
+    # RENDER document part
     document_part_html = document_part_template.render(
         printout_dict=printout_dict,
         imgsrc=os.path.join(imgdir, img_info.get('filename')),
@@ -97,25 +98,28 @@ for answer in site.ask(query):
         fullurl=fullurl,)
     all_document_parts += document_part_html  # append resulting html from document part to the previous parts
 
-    if printout_dict['Part'] == printout_dict['Partof']:  # when Part == Partof
-        # pass all_document_parts html to document_template content
+    if printout_dict['Part'] == printout_dict['Partof']:
+        # RENDER DOCUMENT
+        # by passing all_document_parts html to document_template content
         document_html = document_template.render(title=printout_dict.get('Title'),
                                        date=printout_dict.get('Date'),
                                        content=all_document_parts)  # render document template
         htmlpage_fn = "{}.html".format(printout_dict.get('Title').replace(" ", ""))
+        with open(os.path.join(static_html, htmlpage_fn), 'w') as htmlfile:
+            htmlfile.write(document_html)
+        all_document_parts = ''  # Reset all_document_parts
 
+        # add info to documentslist for index creation
+        # TODO: possibly needs to be a SortedDict
         documentslist.append({'file': htmlpage_fn,
                               'title': printout_dict.get('Title'),
-                              'date': printout_dict.get('Date')
+                              'date': printout_dict.get('Date'),
+                              'creator': printout_dict.get('Creator')
                               })
-        # print(documentslist)
-
-        with open(os.path.join(static_html, htmlpage_fn), 'w') as htmlfile:
-            htmlfile.write(document_html)
-
-        all_document_parts = ''  # Reset all_document_parts
 
+# RENDER index.html from documentslist
 index_html = index_template.render(index='Index',
+                                   query=query,
                                    documentslist=documentslist)
 with open(os.path.join(static_html, 'index.html'), 'w') as htmlfile:
     htmlfile.write(index_html)

static/style.css

@@ -10,3 +10,5 @@ div#content img {width: 50%;}
 
 div.metadata span.key {color: red;
                        font-weight: bold;}
+
+#orc {color:blue;}

templates/index.html

@@ -5,10 +5,12 @@
     <title>{{title}}</title>
 </head>
 <body>
+<h3>Results from query:<br/><code>{{query}}</code></h3>
     <ul>
     {% for doc in documentslist %}
         <li><a href="./{{ doc['file'] }}">{{ doc['title'] }}</a>
        {{ doc['date'].year }}.{{ doc['date'].month }}.{{ doc['date'].day }}
+        {{doc['creator']}}
         </li>
     {% endfor %}
     </ul>