Removed readtime and lxml dependencies

Dockerfile

@@ -47,16 +47,12 @@ RUN \
     git \
     git-fast-import \
     jpeg-dev \
-    libxml2 \
-    libxslt \
     openssh \
     zlib-dev \
 && \
   apk add --no-cache --virtual .build \
     gcc \
     libffi-dev \
-    libxml2-dev \
-    libxslt-dev \
     musl-dev \
 && \
   pip install --no-cache-dir --upgrade pip \

material/plugins/blog/plugin.py

@@ -23,7 +23,6 @@ from __future__ import annotations
 import logging
 import os
 import posixpath
-import readtime
 import yaml
 
 from babel.dates import format_date
@@ -43,6 +42,7 @@ from yaml import SafeLoader
 
 from .author import Authors
 from .config import BlogConfig
+from .readtime import readtime
 from .structure import Archive, Category, Excerpt, Post, View
 from .templates import url_filter
 
@@ -260,17 +260,6 @@ class BlogPlugin(BasePlugin[BlogConfig]):
                 # Append to list of authors
                 page.authors.append(self.authors[name])
 
-        # Compute readtime of post, if enabled and not explicitly set
-        if self.config.post_readtime:
-            rate = self.config.post_readtime_words_per_minute
-
-            # There's a bug in the readtime library which causes it to fail if
-            # the input string contains emojis - see https://t.ly/qEoHq
-            if not page.config.readtime:
-                data = markdown.encode("unicode_escape")
-                read = readtime.of_markdown(data, rate)
-                page.config.readtime = read.minutes
-
         # Extract settings for excerpts
         separator      = self.config.post_excerpt_separator
         max_authors    = self.config.post_excerpt_max_authors
@@ -295,6 +284,22 @@ class BlogPlugin(BasePlugin[BlogConfig]):
         page.excerpt.authors    = page.authors[:max_authors]
         page.excerpt.categories = page.categories[:max_categories]
 
+    # Process posts
+    def on_page_content(self, html, *, page, config, files):
+        if not self.config.enabled:
+            return
+
+        # Skip if page is not a post managed by this instance - this plugin has
+        # support for multiple instances, which is why this check is necessary
+        if page not in self.blog.posts:
+            return
+
+        # Compute readtime of post, if enabled and not explicitly set
+        if self.config.post_readtime:
+            words_per_minute = self.config.post_readtime_words_per_minute
+            if not page.config.readtime:
+                page.config.readtime = readtime(html, words_per_minute)
+
     # Register template filters for plugin
     def on_env(self, env, *, config, files):
         if not self.config.enabled:

material/plugins/blog/readtime/__init__.py

@@ -0,0 +1,74 @@
+# Copyright (c) 2016-2023 Martin Donath <martin.donath@squidfunk.com>
+
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to
+# deal in the Software without restriction, including without limitation the
+# rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+# sell copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+# IN THE SOFTWARE.
+
+import re
+
+from html.parser import HTMLParser
+from math import ceil
+
+# -----------------------------------------------------------------------------
+# Functions
+# -----------------------------------------------------------------------------
+
+# Compute readtime - we first used the original readtime library, but the list
+# of dependencies it brings with it increased the size of the Docker image by
+# 20 MB (packed), which is an increase of 50%. For this reason, we adapt the
+# original readtime algorithm to our needs - see https://t.ly/fPZ7L
+def readtime(html: str, words_per_minute: int):
+    parser = ReadtimeParser()
+    parser.feed(html)
+    parser.close()
+
+    # Extract words from text and compute readtime in seconds
+    words = len(re.split(r"\W+", "".join(parser.text)))
+    seconds = ceil(words / words_per_minute * 60)
+
+    # Account for additional images
+    delta = 12
+    for _ in range(parser.images):
+        seconds += delta
+        if delta > 3: delta -= 1
+
+    # Return readtime in minutes
+    return ceil(seconds / 60)
+
+# -----------------------------------------------------------------------------
+# Classes
+# -----------------------------------------------------------------------------
+
+# Readtime parser
+class ReadtimeParser(HTMLParser):
+
+    # Initialize parser
+    def __init__(self):
+        super().__init__(convert_charrefs = True)
+
+        # Keep track of text and images
+        self.text   = []
+        self.images = 0
+
+    # Collect images
+    def handle_starttag(self, tag, attrs):
+        if tag == "img":
+            self.images += 1
+
+    # Collect text
+    def handle_data(self, data):
+        self.text.append(data)

requirements.txt

@@ -29,8 +29,6 @@ pymdown-extensions>=9.9.1
 # Requirements for plugins
 babel>=2.10.3
 colorama>=0.4
-lxml>=4.6
 paginate>=0.5.6
-readtime>=2.0
 regex>=2022.4.24
 requests>=2.26

src/plugins/blog/plugin.py

@@ -23,7 +23,6 @@ from __future__ import annotations
 import logging
 import os
 import posixpath
-import readtime
 import yaml
 
 from babel.dates import format_date
@@ -43,6 +42,7 @@ from yaml import SafeLoader
 
 from .author import Authors
 from .config import BlogConfig
+from .readtime import readtime
 from .structure import Archive, Category, Excerpt, Post, View
 from .templates import url_filter
 
@@ -260,17 +260,6 @@ class BlogPlugin(BasePlugin[BlogConfig]):
                 # Append to list of authors
                 page.authors.append(self.authors[name])
 
-        # Compute readtime of post, if enabled and not explicitly set
-        if self.config.post_readtime:
-            rate = self.config.post_readtime_words_per_minute
-
-            # There's a bug in the readtime library which causes it to fail if
-            # the input string contains emojis - see https://t.ly/qEoHq
-            if not page.config.readtime:
-                data = markdown.encode("unicode_escape")
-                read = readtime.of_markdown(data, rate)
-                page.config.readtime = read.minutes
-
         # Extract settings for excerpts
         separator      = self.config.post_excerpt_separator
         max_authors    = self.config.post_excerpt_max_authors
@@ -295,6 +284,22 @@ class BlogPlugin(BasePlugin[BlogConfig]):
         page.excerpt.authors    = page.authors[:max_authors]
         page.excerpt.categories = page.categories[:max_categories]
 
+    # Process posts
+    def on_page_content(self, html, *, page, config, files):
+        if not self.config.enabled:
+            return
+
+        # Skip if page is not a post managed by this instance - this plugin has
+        # support for multiple instances, which is why this check is necessary
+        if page not in self.blog.posts:
+            return
+
+        # Compute readtime of post, if enabled and not explicitly set
+        if self.config.post_readtime:
+            words_per_minute = self.config.post_readtime_words_per_minute
+            if not page.config.readtime:
+                page.config.readtime = readtime(html, words_per_minute)
+
     # Register template filters for plugin
     def on_env(self, env, *, config, files):
         if not self.config.enabled:

src/plugins/blog/readtime/__init__.py

@@ -0,0 +1,74 @@
+# Copyright (c) 2016-2023 Martin Donath <martin.donath@squidfunk.com>
+
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to
+# deal in the Software without restriction, including without limitation the
+# rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+# sell copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+# IN THE SOFTWARE.
+
+import re
+
+from html.parser import HTMLParser
+from math import ceil
+
+# -----------------------------------------------------------------------------
+# Functions
+# -----------------------------------------------------------------------------
+
+# Compute readtime - we first used the original readtime library, but the list
+# of dependencies it brings with it increased the size of the Docker image by
+# 20 MB (packed), which is an increase of 50%. For this reason, we adapt the
+# original readtime algorithm to our needs - see https://t.ly/fPZ7L
+def readtime(html: str, words_per_minute: int):
+    parser = ReadtimeParser()
+    parser.feed(html)
+    parser.close()
+
+    # Extract words from text and compute readtime in seconds
+    words = len(re.split(r"\W+", "".join(parser.text)))
+    seconds = ceil(words / words_per_minute * 60)
+
+    # Account for additional images
+    delta = 12
+    for _ in range(parser.images):
+        seconds += delta
+        if delta > 3: delta -= 1
+
+    # Return readtime in minutes
+    return ceil(seconds / 60)
+
+# -----------------------------------------------------------------------------
+# Classes
+# -----------------------------------------------------------------------------
+
+# Readtime parser
+class ReadtimeParser(HTMLParser):
+
+    # Initialize parser
+    def __init__(self):
+        super().__init__(convert_charrefs = True)
+
+        # Keep track of text and images
+        self.text   = []
+        self.images = 0
+
+    # Collect images
+    def handle_starttag(self, tag, attrs):
+        if tag == "img":
+            self.images += 1
+
+    # Collect text
+    def handle_data(self, data):
+        self.text.append(data)