Reading time estimations, fixing #47

README.org

@@ -296,6 +296,8 @@ efficiently:
      the entry page, navigational pages, and the feeds. This way, you
      can publish pages who can only be access by people knowing its URL.
 
+- Reading time estimations (multi-language) following [[https://github.com/novoid/lazyblorg/issues/47][this feature request]]
+
 ** FAQs
 
 See https://github.com/novoid/lazyblorg/wiki/FAQs

lib/htmlizer.py

@@ -1,12 +1,13 @@
 # -*- coding: utf-8; mode: python; -*-
-# Time-stamp: <2020-10-03 16:27:56 vk>
+# Time-stamp: <2020-10-03 16:45:42 vk>
 
 import config  # lazyblorg-global settings
 import sys
 import logging
 import os
 from datetime import datetime
 from time import time, localtime, strftime
+from math import ceil  # for calculating reading time
 import re  # RegEx: for parsing/sanitizing
 import codecs
 from lib.utils import Utils  # for guess_language_from_stopword_percentages()
@@ -313,6 +314,28 @@ def _populate_dict_of_tags_with_ids(self, blog_data):
 
         return dict_of_tags_with_ids
 
+    def _derive_reading_length(self, rawcontent: str) -> int:
+        """
+        Determines the number of minutes reading time from the rawcontent of the article.
+
+        Assumption: people are able to read 250 words per minute.
+
+        See https://github.com/novoid/lazyblorg/issues/47 for the idea and implementation notes.
+        """
+
+        # remove heading title and drawer in order to get body of content:
+        rawcontent_without_header: str = re.sub(r':PROPERTIES:.+?:END:\n', '', rawcontent, flags=re.DOTALL)
+
+        # remove all "words" (according to split()) which contains numbers or other characters that are indicators of non-word elements:
+        raw_words: list = [x for x in rawcontent_without_header.split() if not re.match(r'.*[|0123456789].*', x)]
+        raw_words = [x for x in raw_words if not x.startswith(('#+', '-', ':'))]
+
+        minutes: int = ceil(len(raw_words) / 250)
+
+        if minutes == 0:
+            minutes = 1  # even empty articles should take one minute to watch at
+        return minutes
+
     def _generate_pages_for_tags_persistent_temporal(self, tags):
         """
         Method that creates the pages for tag-pages, persistent pages, and temporal pages.
@@ -348,6 +371,10 @@ def _generate_pages_for_tags_persistent_temporal(self, tags):
 
             entry = self.sanitize_and_htmlize_blog_content(entry)
 
+            # populate reading time indicator:
+            if 'rawcontent' in entry.keys():
+                entry['reading_minutes'] = self._derive_reading_length(entry['rawcontent'])
+
             htmlcontent = None
 
             if entry['category'] == config.TAGS:
@@ -475,6 +502,7 @@ def _generate_tag_page(self, entry):
         htmlcontent += self._replace_general_article_placeholders(
             entry, content)
         htmlcontent = self.sanitize_internal_links(htmlcontent)
+        htmlcontent = self._insert_reading_minutes_if_found(entry, htmlcontent)
 
         return htmlfilename, orgfilename, htmlcontent
 
@@ -1967,6 +1995,53 @@ def _generate_temporal_article(self, entry):
         htmlcontent += self._replace_general_article_placeholders(
             entry, content)
         htmlcontent = self.sanitize_internal_links(htmlcontent)
+        htmlcontent = self._insert_reading_minutes_if_found(entry, htmlcontent)
+
+        return htmlfilename, orgfilename, htmlcontent
+
+    def _insert_reading_minutes_if_found(self, entry, htmlcontent):
+        """
+        Handles the snippet that contains the estimation for the reading minutes.
+        Deletes the snippet of the template if none found.
+        """
+        content = ''
+        if 'reading_minutes' in entry.keys():
+            if '#READING-MINUTES-SECTION#' in htmlcontent:
+                # insert snippet
+                snippetname = 'reading-time-'
+
+                # handle one or many minutes: (I do have different snippets for those cases)
+                if entry['reading_minutes'] == 1:
+                    snippetname += 'one-minute-'
+                else:
+                    snippetname += 'multiple-minutes-'
+
+                # handle different languages:
+                if entry['autotags']['language'] == 'deutsch':
+                    # FIXXME: other languages than german have to be added
+                    # here: (generalize using a configured list of known
+                    # languages?)
+                    snippetname += 'de'
+                else:
+                    snippetname += 'en'
+
+                # insert snippet:
+                content = htmlcontent.replace('#READING-MINUTES-SECTION#', self.template_definition_by_name(snippetname))
+                # replace actual minutes (if found):
+                content = self._replace_general_article_placeholders(entry, content)
+                return content
+            else:
+                # remove template snippet because we've got no minutes to insert
+                # NOTE: Should be dead code
+                logging.warning('Entry %s: missing reading minutes, removing snippet' % entry['id'])
+                return htmlcontent.replace('#READING-MINUTES-SECTION#', '')
+        else:
+            # missing reading minutes should only be OK with
+            # auto-generated tag pages. Report error if otherwise:
+            if not entry['id'].startswith(self.ID_PREFIX_FOR_EMPTY_TAG_PAGES):
+                logging.warning('Entry %s: missing reading minutes in "entry[]"' % entry['id'])
+            return htmlcontent
+
 
         return htmlfilename, orgfilename, htmlcontent
 
@@ -2018,6 +2093,7 @@ def _generate_persistent_article(self, entry):
         htmlcontent += self._replace_general_article_placeholders(
             entry, content)
         htmlcontent = self.sanitize_internal_links(htmlcontent)
+        htmlcontent = self._insert_reading_minutes_if_found(entry, htmlcontent)
 
         return htmlfilename, orgfilename, htmlcontent
 
@@ -2158,6 +2234,9 @@ def _replace_general_article_placeholders(self, entry, template):
                 self._generate_tag_page_list(
                     entry['title']))
 
+        if 'reading_minutes' in entry.keys():
+            content = content.replace('#READINGMINUTES#', str(entry['reading_minutes']))
+
         return content
 
     def _generate_top_tag_list(self):

templates/blog-format.org

@@ -283,6 +283,36 @@ With name/label:
 
 #+END_EXPORT
 
+*** Reading time indicators
+
+#+NAME: reading-time-one-minute-en
+#+BEGIN_HTML
+	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+#+END_HTML
+
+#+NAME: reading-time-one-minute-de
+#+BEGIN_HTML
+	  <aside class="reading-time-section">
+          Lesezeit ist eine Minute
+	  </aside>
+#+END_HTML
+
+#+NAME: reading-time-multiple-minutes-en
+#+BEGIN_HTML
+	  <aside class="reading-time-section">
+          Reading time is #READINGMINUTES# minutes
+	  </aside>
+#+END_HTML
+
+#+NAME: reading-time-multiple-minutes-de
+#+BEGIN_HTML
+	  <aside class="reading-time-section">
+          Lesezeit ist #READINGMINUTES# Minuten
+	  </aside>
+#+END_HTML
+
 *** ignore me
 
 #+NAME:
@@ -542,6 +572,8 @@ With name/label:
 
 	  <h1 class="common-article-header-title">#ARTICLE-TITLE#</h1>
 
+    #READING-MINUTES-SECTION#
+
 	</header>
 
     #COMMON-SIDEBAR#
@@ -730,6 +762,8 @@ With name/label:
 
 	  <h1 class="common-article-header-title">#ARTICLE-TITLE#</h1>
 
+  #READING-MINUTES-SECTION#
+
 	</header>
 
   #COMMON-SIDEBAR#
@@ -1029,6 +1063,8 @@ Pages that describe a tag. Corresponding Org-mode entries must have:
 
 	  <h1 class="common-article-header-title">Tag Page for the Tag "#ARTICLE-TITLE#"</h1>
 
+    #READING-MINUTES-SECTION#
+
 	</header>
 
   #COMMON-SIDEBAR#

templates/public_voit.scss

@@ -512,6 +512,17 @@ figcaption {
     font-size: 80%;
 }
 
+.reading-time-section {
+    @extend .middle_section_wide;
+    font-size: 80%;
+    color: gray;
+    text-align: right;
+    margin-left: auto;
+    margin-right: auto;
+    /* padding-top: 0.2em;*/
+    padding-right: 15em;
+}
+
 .published-on {
     @extend .middle_section_wide;
     font-size: 80%;

testdata/end_to_end_test/comparison/1985/01/01/old-entry1/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry1</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>
 
 

testdata/end_to_end_test/comparison/1985/01/01/old-entry10/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry10</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>
 
 

testdata/end_to_end_test/comparison/1985/01/01/old-entry11/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry11</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>
 
 

testdata/end_to_end_test/comparison/1985/01/01/old-entry12/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry12</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>
 
 

testdata/end_to_end_test/comparison/1985/01/01/old-entry13/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry13</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>
 
 

testdata/end_to_end_test/comparison/1985/01/01/old-entry14/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry14</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>
 
 

testdata/end_to_end_test/comparison/1985/01/01/old-entry2/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry2</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>
 
 

testdata/end_to_end_test/comparison/1985/01/01/old-entry3/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry3</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>
 
 

testdata/end_to_end_test/comparison/1985/01/01/old-entry4/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry4</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>
 
 

testdata/end_to_end_test/comparison/1985/01/01/old-entry5/index.html

@@ -59,6 +59,10 @@
 
 	  <h1 class="common-article-header-title">old blog entry5</h1>
 
+  	  <aside class="reading-time-section">
+          Reading time is one minute
+	  </aside>
+
 	</header>