Merge branch 'master' into add_option_remove_indentation

Author: Salka1988

Cargo.lock

@@ -20,9 +20,9 @@ anyhow = "1.0.28"
 chrono = "0.4"
 clap = { version = "3.0", features = ["cargo"] }
 clap_complete = "3.0"
+once_cell = "1"
 env_logger = "0.9.0"
 handlebars = "4.0"
-lazy_static = "1.0"
 log = "0.4"
 memchr = "2.0"
 opener = "0.5"
@@ -65,3 +65,7 @@ search = ["elasticlunr-rs", "ammonia"]
 [[bin]]
 doc = false
 name = "mdbook"
+
+[[example]]
+name = "nop-preprocessor"
+test = true

Cargo.toml

@@ -101,4 +101,58 @@ mod nop_lib {
             renderer != "not-supported"
         }
     }
+
+    #[cfg(test)]
+    mod test {
+        use super::*;
+
+        #[test]
+        fn nop_preprocessor_run() {
+            let input_json = r##"[
+                {
+                    "root": "/path/to/book",
+                    "config": {
+                        "book": {
+                            "authors": ["AUTHOR"],
+                            "language": "en",
+                            "multilingual": false,
+                            "src": "src",
+                            "title": "TITLE"
+                        },
+                        "preprocessor": {
+                            "nop": {}
+                        }
+                    },
+                    "renderer": "html",
+                    "mdbook_version": "0.4.21"
+                },
+                {
+                    "sections": [
+                        {
+                            "Chapter": {
+                                "name": "Chapter 1",
+                                "content": "# Chapter 1\n",
+                                "number": [1],
+                                "sub_items": [],
+                                "path": "chapter_1.md",
+                                "source_path": "chapter_1.md",
+                                "parent_names": []
+                            }
+                        }
+                    ],
+                    "__non_exhaustive": null
+                }
+            ]"##;
+            let input_json = input_json.as_bytes();
+
+            let (ctx, book) = mdbook::preprocess::CmdPreprocessor::parse_input(input_json).unwrap();
+            let expected_book = book.clone();
+            let result = Nop::new().run(&ctx, book);
+            assert!(result.is_ok());
+
+            // The nop-preprocessor should not have made any changes to the book content.
+            let actual_book = result.unwrap();
+            assert_eq!(actual_book, expected_book);
+        }
+    }
 }

examples/nop-preprocessor.rs

@@ -4,8 +4,8 @@ use std::path::Path;
 use super::{Preprocessor, PreprocessorContext};
 use crate::book::{Book, BookItem};
 use crate::errors::*;
-use lazy_static::lazy_static;
 use log::warn;
+use once_cell::sync::Lazy;
 
 /// A preprocessor for converting file name `README.md` to `index.md` since
 /// `README.md` is the de facto index file in markdown-based documentation.
@@ -68,9 +68,8 @@ fn warn_readme_name_conflict<P: AsRef<Path>>(readme_path: P, index_path: P) {
 }
 
 fn is_readme_file<P: AsRef<Path>>(path: P) -> bool {
-    lazy_static! {
-        static ref RE: Regex = Regex::new(r"(?i)^readme$").unwrap();
-    }
+    static RE: Lazy<Regex> = Lazy::new(|| Regex::new(r"(?i)^readme$").unwrap());
+
     RE.is_match(
         path.as_ref()
             .file_stem()

src/preprocess/index.rs

@@ -10,8 +10,8 @@ use std::path::{Path, PathBuf};
 
 use super::{Preprocessor, PreprocessorContext};
 use crate::book::{Book, BookItem};
-use lazy_static::lazy_static;
 use log::{error, warn};
+use once_cell::sync::Lazy;
 
 const ESCAPE_CHAR: char = '\\';
 const MAX_LINK_NESTED_DEPTH: usize = 10;
@@ -436,19 +436,20 @@ impl<'a> Iterator for LinkIter<'a> {
 fn find_links(contents: &str) -> LinkIter<'_> {
     // lazily compute following regex
     // r"\\\{\{#.*\}\}|\{\{#([a-zA-Z0-9]+)\s*([^}]+)\}\}")?;
-    lazy_static! {
-        static ref RE: Regex = Regex::new(
+    static RE: Lazy<Regex> = Lazy::new(|| {
+        Regex::new(
             r"(?x)              # insignificant whitespace mode
-            \\\{\{\#.*\}\}      # match escaped link
-            |                   # or
-            \{\{\s*             # link opening parens and whitespace
-            \#([a-zA-Z0-9_]+)   # link type
-            \s+                 # separating whitespace
-            ([^}]+)             # link target path and space separated properties
-            \}\}                # link closing parens"
+        \\\{\{\#.*\}\}      # match escaped link
+        |                   # or
+        \{\{\s*             # link opening parens and whitespace
+        \#([a-zA-Z0-9_]+)   # link type
+        \s+                 # separating whitespace
+        ([^}]+)             # link target path and space separated properties
+        \}\}                # link closing parens",
         )
-        .unwrap();
-    }
+        .unwrap()
+    });
+
     LinkIter(RE.captures_iter(contents))
 }
 

src/preprocess/links.rs

@@ -14,8 +14,8 @@ use std::path::{Path, PathBuf};
 
 use crate::utils::fs::get_404_output_file;
 use handlebars::Handlebars;
-use lazy_static::lazy_static;
 use log::{debug, trace, warn};
+use once_cell::sync::Lazy;
 use regex::{Captures, Regex};
 use serde_json::json;
 
@@ -767,9 +767,8 @@ fn make_data(
 /// Goes through the rendered HTML, making sure all header tags have
 /// an anchor respectively so people can link to sections directly.
 fn build_header_links(html: &str) -> String {
-    lazy_static! {
-        static ref BUILD_HEADER_LINKS: Regex = Regex::new(r"<h(\d)>(.*?)</h\d>").unwrap();
-    }
+    static BUILD_HEADER_LINKS: Lazy<Regex> =
+        Lazy::new(|| Regex::new(r"<h(\d)>(.*?)</h\d>").unwrap());
 
     let mut id_counter = HashMap::new();
 
@@ -810,10 +809,8 @@ fn insert_link_into_header(
 // ```
 // This function replaces all commas by spaces in the code block classes
 fn fix_code_blocks(html: &str) -> String {
-    lazy_static! {
-        static ref FIX_CODE_BLOCKS: Regex =
-            Regex::new(r##"<code([^>]+)class="([^"]+)"([^>]*)>"##).unwrap();
-    }
+    static FIX_CODE_BLOCKS: Lazy<Regex> =
+        Lazy::new(|| Regex::new(r##"<code([^>]+)class="([^"]+)"([^>]*)>"##).unwrap());
 
     FIX_CODE_BLOCKS
         .replace_all(html, |caps: &Captures<'_>| {
@@ -836,10 +833,9 @@ fn add_playground_pre(
     playground_config: &Playground,
     edition: Option<RustEdition>,
 ) -> String {
-    lazy_static! {
-        static ref ADD_PLAYGROUND_PRE: Regex =
-            Regex::new(r##"((?s)<code[^>]?class="([^"]+)".*?>(.*?)</code>)"##).unwrap();
-    }
+    static ADD_PLAYGROUND_PRE: Lazy<Regex> =
+        Lazy::new(|| Regex::new(r##"((?s)<code[^>]?class="([^"]+)".*?>(.*?)</code>)"##).unwrap());
+
     ADD_PLAYGROUND_PRE
         .replace_all(html, |caps: &Captures<'_>| {
             let text = &caps[1];
@@ -902,9 +898,7 @@ fn add_playground_pre(
 }
 
 fn hide_lines(content: &str) -> String {
-    lazy_static! {
-        static ref BORING_LINES_REGEX: Regex = Regex::new(r"^(\s*)#(.?)(.*)$").unwrap();
-    }
+    static BORING_LINES_REGEX: Lazy<Regex> = Lazy::new(|| Regex::new(r"^(\s*)#(.?)(.*)$").unwrap());
 
     let mut result = String::with_capacity(content.len());
     let mut lines = content.lines().peekable();

src/renderer/html_handlebars/hbs_renderer.rs

@@ -3,14 +3,14 @@ use std::collections::{HashMap, HashSet};
 use std::path::Path;
 
 use elasticlunr::{Index, IndexBuilder};
+use once_cell::sync::Lazy;
 use pulldown_cmark::*;
 
 use crate::book::{Book, BookItem};
 use crate::config::Search;
 use crate::errors::*;
 use crate::theme::searcher;
 use crate::utils;
-use lazy_static::lazy_static;
 use log::{debug, warn};
 use serde::Serialize;
 
@@ -267,21 +267,19 @@ fn write_to_json(index: Index, search_config: &Search, doc_urls: Vec<String>) ->
 }
 
 fn clean_html(html: &str) -> String {
-    lazy_static! {
-        static ref AMMONIA: ammonia::Builder<'static> = {
-            let mut clean_content = HashSet::new();
-            clean_content.insert("script");
-            clean_content.insert("style");
-            let mut builder = ammonia::Builder::new();
-            builder
-                .tags(HashSet::new())
-                .tag_attributes(HashMap::new())
-                .generic_attributes(HashSet::new())
-                .link_rel(None)
-                .allowed_classes(HashMap::new())
-                .clean_content_tags(clean_content);
-            builder
-        };
-    }
+    static AMMONIA: Lazy<ammonia::Builder<'static>> = Lazy::new(|| {
+        let mut clean_content = HashSet::new();
+        clean_content.insert("script");
+        clean_content.insert("style");
+        let mut builder = ammonia::Builder::new();
+        builder
+            .tags(HashSet::new())
+            .tag_attributes(HashMap::new())
+            .generic_attributes(HashSet::new())
+            .link_rel(None)
+            .allowed_classes(HashMap::new())
+            .clean_content_tags(clean_content);
+        builder
+    });
     AMMONIA.clean(html).to_string()
 }

src/renderer/html_handlebars/search.rs

@@ -4,8 +4,8 @@ pub mod fs;
 mod string;
 pub(crate) mod toml_ext;
 use crate::errors::Error;
-use lazy_static::lazy_static;
 use log::error;
+use once_cell::sync::Lazy;
 use pulldown_cmark::{html, CodeBlockKind, CowStr, Event, Options, Parser, Tag};
 use regex::Regex;
 
@@ -21,9 +21,7 @@ pub use self::string::{
 
 /// Replaces multiple consecutive whitespace characters with a single space character.
 pub fn collapse_whitespace(text: &str) -> Cow<'_, str> {
-    lazy_static! {
-        static ref RE: Regex = Regex::new(r"\s\s+").unwrap();
-    }
+    static RE: Lazy<Regex> = Lazy::new(|| Regex::new(r"\s\s+").unwrap());
     RE.replace_all(text, " ")
 }
 
@@ -52,9 +50,7 @@ pub fn id_from_content(content: &str) -> String {
     let mut content = content.to_string();
 
     // Skip any tags or html-encoded stuff
-    lazy_static! {
-        static ref HTML: Regex = Regex::new(r"(<.*?>)").unwrap();
-    }
+    static HTML: Lazy<Regex> = Lazy::new(|| Regex::new(r"(<.*?>)").unwrap());
     content = HTML.replace_all(&content, "").into();
     const REPL_SUB: &[&str] = &["&lt;", "&gt;", "&amp;", "&#39;", "&quot;"];
     for sub in REPL_SUB {
@@ -97,10 +93,9 @@ pub fn unique_id_from_content(content: &str, id_counter: &mut HashMap<String, us
 /// None. Ideally, print page links would link to anchors on the print page,
 /// but that is very difficult.
 fn adjust_links<'a>(event: Event<'a>, path: Option<&Path>) -> Event<'a> {
-    lazy_static! {
-        static ref SCHEME_LINK: Regex = Regex::new(r"^[a-z][a-z0-9+.-]*:").unwrap();
-        static ref MD_LINK: Regex = Regex::new(r"(?P<link>.*)\.md(?P<anchor>#.*)?").unwrap();
-    }
+    static SCHEME_LINK: Lazy<Regex> = Lazy::new(|| Regex::new(r"^[a-z][a-z0-9+.-]*:").unwrap());
+    static MD_LINK: Lazy<Regex> =
+        Lazy::new(|| Regex::new(r"(?P<link>.*)\.md(?P<anchor>#.*)?").unwrap());
 
     fn fix<'a>(dest: CowStr<'a>, path: Option<&Path>) -> CowStr<'a> {
         if dest.starts_with('#') {
@@ -153,10 +148,8 @@ fn adjust_links<'a>(event: Event<'a>, path: Option<&Path>) -> Event<'a> {
         // There are dozens of HTML tags/attributes that contain paths, so
         // feel free to add more tags if desired; these are the only ones I
         // care about right now.
-        lazy_static! {
-            static ref HTML_LINK: Regex =
-                Regex::new(r#"(<(?:a|img) [^>]*?(?:src|href)=")([^"]+?)""#).unwrap();
-        }
+        static HTML_LINK: Lazy<Regex> =
+            Lazy::new(|| Regex::new(r#"(<(?:a|img) [^>]*?(?:src|href)=")([^"]+?)""#).unwrap());
 
         HTML_LINK
             .replace_all(&html, |caps: &regex::Captures<'_>| {

src/utils/mod.rs

@@ -1,5 +1,6 @@
 use anyhow::Error;
 use lazy_static::lazy_static;
+use once_cell::sync::Lazy;
 use regex::Regex;
 use std::ops::Bound::{Excluded, Included, Unbounded};
 use std::ops::RangeBounds;
@@ -25,10 +26,10 @@ pub fn take_lines<R: RangeBounds<usize>>(s: &str, range: R) -> String {
     }
 }
 
-lazy_static! {
-    static ref ANCHOR_START: Regex = Regex::new(r"ANCHOR:\s*(?P<anchor_name>[\w_-]+)").unwrap();
-    static ref ANCHOR_END: Regex = Regex::new(r"ANCHOR_END:\s*(?P<anchor_name>[\w_-]+)").unwrap();
-}
+static ANCHOR_START: Lazy<Regex> =
+    Lazy::new(|| Regex::new(r"ANCHOR:\s*(?P<anchor_name>[\w_-]+)").unwrap());
+static ANCHOR_END: Lazy<Regex> =
+    Lazy::new(|| Regex::new(r"ANCHOR_END:\s*(?P<anchor_name>[\w_-]+)").unwrap());
 
 /// Take anchored lines from a string.
 /// Lines containing anchor are ignored.