From 6b0f468f9fc1a62879f644f1d78205c1a2c9da01 Mon Sep 17 00:00:00 2001
From: PoiScript <poiscript@gmail.com>
Date: Fri, 28 Jun 2019 18:00:49 +0800
Subject: [PATCH] feat(org): ParseConfig struct

---
 README.md                |  63 ++++++++++---------
 src/config.rs            |  19 ++++++
 src/elements/headline.rs | 129 +++++++++++++++++++++++++++++++--------
 src/elements/mod.rs      |   2 +-
 src/lib.rs               |  97 ++++++++++++-----------------
 src/org.rs               |  27 +++++++-
 6 files changed, 222 insertions(+), 115 deletions(-)
 create mode 100644 src/config.rs

diff --git a/README.md b/README.md
index d173c09..d8c3837 100644
--- a/README.md
+++ b/README.md
@@ -13,14 +13,22 @@ To parse a orgmode string, simply invoking the `Org::parse` function:
 ```rust
 use orgize::Org;
 
-let org = Org::parse(r#"* Title 1
-*Section 1*
-** Title 2
-_Section 2_
-* Title 3
-/Section 3/
-* Title 4
-=Section 4="#);
+Org::parse("* DONE Title :tag:");
+```
+
+or `Org::parse_with_config`:
+
+``` rust
+use orgize::{Org, ParseConfig};
+
+let org = Org::parse_with_config(
+    "* TASK Title 1",
+    ParseConfig {
+        // custom todo keywords
+        todo_keywords: &["TASK"],
+        ..Default::default()
+    },
+);
 ```
 
 ## Iter
@@ -29,7 +37,9 @@ _Section 2_
 a simple wrapper of `Element`.
 
 ```rust
-for event in org.iter() {
+use orgize::Org;
+
+for event in Org::parse("* DONE Title :tag:").iter() {
     // handling the event
 }
 ```
@@ -43,15 +53,14 @@ You can call the `Org::html_default` function to generate html directly, which
 uses the `DefaultHtmlHandler` internally:
 
 ```rust
+use orgize::Org;
+
 let mut writer = Vec::new();
-org.html_default(&mut writer).unwrap();
+Org::parse("* title\n*section*").html_default(&mut writer).unwrap();
 
 assert_eq!(
     String::from_utf8(writer).unwrap(),
-    "<main><h1>Title 1</h1><section><p><b>Section 1</b></p></section>\
-    <h2>Title 2</h2><section><p><u>Section 2</u></p></section>\
-    <h1>Title 3</h1><section><p><i>Section 3</i></p></section>\
-    <h1>Title 4</h1><section><p><code>Section 4</code></p></section></main>"
+    "<main><h1>title</h1><section><p><b>section</b></p></section></main>"
 );
 ```
 
@@ -64,6 +73,14 @@ The following code demonstrates how to add a id for every headline and return
 own error type while rendering.
 
 ```rust
+use std::convert::From;
+use std::io::{Error as IOError, Write};
+use std::string::FromUtf8Error;
+
+use orgize::export::{html::Escape, DefaultHtmlHandler, HtmlHandler};
+use orgize::{Element, Org};
+use slugify::slugify;
+
 #[derive(Debug)]
 enum MyError {
     IO(IOError),
@@ -112,23 +129,13 @@ impl HtmlHandler<MyError> for MyHtmlHandler {
 }
 
 fn main() -> Result<(), MyError> {
-    let contents = r"* Title 1
-*Section 1*
-** Title 2
-_Section 2_
-* Title 3
-/Section 3/
-* Title 4
-=Section 4=";
-
     let mut writer = Vec::new();
-    Org::parse(&contents).html(&mut writer, MyHtmlHandler)?;
+    Org::parse("* title\n*section*").html(&mut writer, MyHtmlHandler)?;
+
     assert_eq!(
         String::from_utf8(writer)?,
-        "<main><h1><a id=\"title-1\" href=\"#title-1\">Title 1</a></h1><section><p><b>Section 1</b></p></section>\
-         <h2><a id=\"title-2\" href=\"#title-2\">Title 2</a></h2><section><p><u>Section 2</u></p></section>\
-         <h1><a id=\"title-3\" href=\"#title-3\">Title 3</a></h1><section><p><i>Section 3</i></p></section>\
-         <h1><a id=\"title-4\" href=\"#title-4\">Title 4</a></h1><section><p><code>Section 4</code></p></section></main>"
+        "<main><h1><a id=\"title\" href=\"#title\">title</a></h1>\
+         <section><p><b>section</b></p></section></main>"
     );
 
     Ok(())
diff --git a/src/config.rs b/src/config.rs
new file mode 100644
index 0000000..5b829d8
--- /dev/null
+++ b/src/config.rs
@@ -0,0 +1,19 @@
+//! Parse configuration module
+
+/// Parse configuration
+#[derive(Clone, Debug)]
+pub struct ParseConfig<'a> {
+    /// Default headline todo keywords, it shouldn't be changed.
+    pub default_todo_keywords: &'a [&'a str],
+    /// Custom headline todo keywords
+    pub todo_keywords: &'a [&'a str],
+}
+
+impl Default for ParseConfig<'_> {
+    fn default() -> Self {
+        ParseConfig {
+            default_todo_keywords: &["TODO", "DONE", "NEXT", "WAITING", "LATER", "CANCELLED"],
+            todo_keywords: &[],
+        }
+    }
+}
diff --git a/src/elements/headline.rs b/src/elements/headline.rs
index 8717baa..ea74e1b 100644
--- a/src/elements/headline.rs
+++ b/src/elements/headline.rs
@@ -3,8 +3,7 @@
 use jetscii::ByteSubstring;
 use memchr::{memchr, memchr2, memrchr};
 
-pub const DEFAULT_TODO_KEYWORDS: &[&str] =
-    &["TODO", "DONE", "NEXT", "WAITING", "LATER", "CANCELLED"];
+use crate::config::ParseConfig;
 
 #[cfg_attr(test, derive(PartialEq))]
 #[cfg_attr(feature = "serde", derive(serde::Serialize))]
@@ -26,7 +25,10 @@ pub struct Headline<'a> {
 }
 
 impl Headline<'_> {
-    pub(crate) fn parse<'a>(text: &'a str, keywords: &[&str]) -> (Headline<'a>, usize, usize) {
+    pub(crate) fn parse<'a>(
+        text: &'a str,
+        config: &ParseConfig<'_>,
+    ) -> (Headline<'a>, usize, usize) {
         let level = memchr2(b'\n', b' ', text.as_bytes()).unwrap_or_else(|| text.len());
 
         debug_assert!(level > 0);
@@ -65,7 +67,8 @@ impl Headline<'_> {
             let (word, off) = memchr(b' ', tail.as_bytes())
                 .map(|i| (&tail[0..i], i + 1))
                 .unwrap_or_else(|| (tail, tail.len()));
-            if keywords.contains(&word) {
+            if config.todo_keywords.contains(&word) || config.default_todo_keywords.contains(&word)
+            {
                 (Some(word), &tail[off..])
             } else {
                 (None, tail)
@@ -149,7 +152,11 @@ impl Headline<'_> {
 #[test]
 fn parse() {
     assert_eq!(
-        Headline::parse("**** DONE [#A] COMMENT Title :tag:a2%:", &["DONE"]).0,
+        Headline::parse(
+            "**** DONE [#A] COMMENT Title :tag:a2%:",
+            &ParseConfig::default()
+        )
+        .0,
         Headline {
             level: 4,
             priority: Some('A'),
@@ -159,7 +166,11 @@ fn parse() {
         },
     );
     assert_eq!(
-        Headline::parse("**** ToDO [#A] COMMENT Title :tag:a2%:", &["DONE"]).0,
+        Headline::parse(
+            "**** ToDO [#A] COMMENT Title :tag:a2%:",
+            &ParseConfig::default()
+        )
+        .0,
         Headline {
             level: 4,
             priority: None,
@@ -169,7 +180,11 @@ fn parse() {
         },
     );
     assert_eq!(
-        Headline::parse("**** T0DO [#A] COMMENT Title :tag:a2%:", &["DONE"]).0,
+        Headline::parse(
+            "**** T0DO [#A] COMMENT Title :tag:a2%:",
+            &ParseConfig::default()
+        )
+        .0,
         Headline {
             level: 4,
             priority: None,
@@ -179,7 +194,11 @@ fn parse() {
         },
     );
     assert_eq!(
-        Headline::parse("**** DONE [#1] COMMENT Title :tag:a2%:", &["DONE"]).0,
+        Headline::parse(
+            "**** DONE [#1] COMMENT Title :tag:a2%:",
+            &ParseConfig::default()
+        )
+        .0,
         Headline {
             level: 4,
             priority: None,
@@ -189,7 +208,11 @@ fn parse() {
         },
     );
     assert_eq!(
-        Headline::parse("**** DONE [#a] COMMENT Title :tag:a2%:", &["DONE"]).0,
+        Headline::parse(
+            "**** DONE [#a] COMMENT Title :tag:a2%:",
+            &ParseConfig::default()
+        )
+        .0,
         Headline {
             level: 4,
             priority: None,
@@ -199,7 +222,11 @@ fn parse() {
         },
     );
     assert_eq!(
-        Headline::parse("**** DONE [#A] COMMENT Title :tag:a2%", &["DONE"]).0,
+        Headline::parse(
+            "**** DONE [#A] COMMENT Title :tag:a2%",
+            &ParseConfig::default()
+        )
+        .0,
         Headline {
             level: 4,
             priority: Some('A'),
@@ -209,7 +236,11 @@ fn parse() {
         },
     );
     assert_eq!(
-        Headline::parse("**** DONE [#A] COMMENT Title tag:a2%:", &["DONE"]).0,
+        Headline::parse(
+            "**** DONE [#A] COMMENT Title tag:a2%:",
+            &ParseConfig::default()
+        )
+        .0,
         Headline {
             level: 4,
             priority: Some('A'),
@@ -219,7 +250,7 @@ fn parse() {
         },
     );
     assert_eq!(
-        Headline::parse("**** COMMENT Title tag:a2%:", &["DONE"]).0,
+        Headline::parse("**** COMMENT Title tag:a2%:", &ParseConfig::default()).0,
         Headline {
             level: 4,
             priority: None,
@@ -233,7 +264,14 @@ fn parse() {
 #[test]
 fn parse_todo_keywords() {
     assert_eq!(
-        Headline::parse("**** DONE [#A] COMMENT Title :tag:a2%:", &[]).0,
+        Headline::parse(
+            "**** DONE [#A] COMMENT Title :tag:a2%:",
+            &ParseConfig {
+                default_todo_keywords: &[],
+                ..Default::default()
+            }
+        )
+        .0,
         Headline {
             level: 4,
             priority: None,
@@ -243,7 +281,14 @@ fn parse_todo_keywords() {
         },
     );
     assert_eq!(
-        Headline::parse("**** TASK [#A] COMMENT Title :tag:a2%:", &["TASK"]).0,
+        Headline::parse(
+            "**** TASK [#A] COMMENT Title :tag:a2%:",
+            &ParseConfig {
+                todo_keywords: &["TASK"],
+                ..Default::default()
+            }
+        )
+        .0,
         Headline {
             level: 4,
             priority: Some('A'),
@@ -256,21 +301,55 @@ fn parse_todo_keywords() {
 
 #[test]
 fn is_commented() {
-    assert!(Headline::parse("* COMMENT Title", &[]).0.is_commented());
-    assert!(!Headline::parse("* Title", &[]).0.is_commented());
-    assert!(!Headline::parse("* C0MMENT Title", &[]).0.is_commented());
-    assert!(!Headline::parse("* comment Title", &[]).0.is_commented());
+    assert!(Headline::parse("* COMMENT Title", &ParseConfig::default())
+        .0
+        .is_commented());
+    assert!(!Headline::parse("* Title", &ParseConfig::default())
+        .0
+        .is_commented());
+    assert!(!Headline::parse("* C0MMENT Title", &ParseConfig::default())
+        .0
+        .is_commented());
+    assert!(!Headline::parse("* comment Title", &ParseConfig::default())
+        .0
+        .is_commented());
 }
 
 #[test]
 fn is_archived() {
-    assert!(Headline::parse("* Title :ARCHIVE:", &[]).0.is_archived());
-    assert!(Headline::parse("* Title :t:ARCHIVE:", &[]).0.is_archived());
-    assert!(Headline::parse("* Title :ARCHIVE:t:", &[]).0.is_archived());
-    assert!(!Headline::parse("* Title", &[]).0.is_commented());
-    assert!(!Headline::parse("* Title :ARCHIVED:", &[]).0.is_archived());
-    assert!(!Headline::parse("* Title :ARCHIVES:", &[]).0.is_archived());
-    assert!(!Headline::parse("* Title :archive:", &[]).0.is_archived());
+    assert!(
+        Headline::parse("* Title :ARCHIVE:", &ParseConfig::default())
+            .0
+            .is_archived()
+    );
+    assert!(
+        Headline::parse("* Title :t:ARCHIVE:", &ParseConfig::default())
+            .0
+            .is_archived()
+    );
+    assert!(
+        Headline::parse("* Title :ARCHIVE:t:", &ParseConfig::default())
+            .0
+            .is_archived()
+    );
+    assert!(!Headline::parse("* Title", &ParseConfig::default())
+        .0
+        .is_commented());
+    assert!(
+        !Headline::parse("* Title :ARCHIVED:", &ParseConfig::default())
+            .0
+            .is_archived()
+    );
+    assert!(
+        !Headline::parse("* Title :ARCHIVES:", &ParseConfig::default())
+            .0
+            .is_archived()
+    );
+    assert!(
+        !Headline::parse("* Title :archive:", &ParseConfig::default())
+            .0
+            .is_archived()
+    );
 }
 
 #[test]
diff --git a/src/elements/mod.rs b/src/elements/mod.rs
index 9044599..3b71b81 100644
--- a/src/elements/mod.rs
+++ b/src/elements/mod.rs
@@ -32,7 +32,7 @@ pub use self::{
     dyn_block::DynBlock,
     fn_def::FnDef,
     fn_ref::FnRef,
-    headline::{Headline, DEFAULT_TODO_KEYWORDS},
+    headline::Headline,
     inline_call::InlineCall,
     inline_src::InlineSrc,
     keyword::{BabelCall, Keyword},
diff --git a/src/lib.rs b/src/lib.rs
index 724ee86..196c506 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -9,14 +9,24 @@
 //! ```rust
 //! use orgize::Org;
 //!
-//! let org = Org::parse(r#"* Title 1
-//! *Section 1*
-//! ** Title 2
-//! _Section 2_
-//! * Title 3
-//! /Section 3/
-//! * Title 4
-//! =Section 4="#);
+//! Org::parse("* DONE Title :tag:");
+//! ```
+//!
+//! or [`Org::parse_with_config`]:
+//!
+//! [`Org::parse_with_config`]: org/struct.Org.html#method.parse_with_config
+//!
+//! ``` rust
+//! use orgize::{Org, ParseConfig};
+//!
+//! Org::parse_with_config(
+//!     "* TASK Title 1",
+//!     ParseConfig {
+//!         // custom todo keywords
+//!         todo_keywords: &["TASK"],
+//!         ..Default::default()
+//!     },
+//! );
 //! ```
 //!
 //! # Iter
@@ -29,18 +39,9 @@
 //! [`Element`]: elements/enum.Element.html
 //!
 //! ```rust
-//! # use orgize::Org;
-//! #
-//! # let org = Org::parse(r#"* Title 1
-//! # *Section 1*
-//! # ** Title 2
-//! # _Section 2_
-//! # * Title 3
-//! # /Section 3/
-//! # * Title 4
-//! # =Section 4="#);
-//! #
-//! for event in org.iter() {
+//! use orgize::Org;
+//!
+//! for event in Org::parse("* DONE Title :tag:").iter() {
 //!     // handling the event
 //! }
 //! ```
@@ -60,26 +61,14 @@
 //! [`DefaultHtmlHandler`]: export/html/struct.DefaultHtmlHandler.html
 //!
 //! ```rust
-//! # use orgize::Org;
-//! #
-//! # let org = Org::parse(r#"* Title 1
-//! # *Section 1*
-//! # ** Title 2
-//! # _Section 2_
-//! # * Title 3
-//! # /Section 3/
-//! # * Title 4
-//! # =Section 4="#);
-//! #
+//! use orgize::Org;
+//!
 //! let mut writer = Vec::new();
-//! org.html_default(&mut writer).unwrap();
+//! Org::parse("* title\n*section*").html_default(&mut writer).unwrap();
 //!
 //! assert_eq!(
 //!     String::from_utf8(writer).unwrap(),
-//!     "<main><h1>Title 1</h1><section><p><b>Section 1</b></p></section>\
-//!     <h2>Title 2</h2><section><p><u>Section 2</u></p></section>\
-//!     <h1>Title 3</h1><section><p><i>Section 3</i></p></section>\
-//!     <h1>Title 4</h1><section><p><code>Section 4</code></p></section></main>"
+//!     "<main><h1>title</h1><section><p><b>section</b></p></section></main>"
 //! );
 //! ```
 //!
@@ -95,14 +84,14 @@
 //! own error type while rendering.
 //!
 //! ```rust
-//! # use std::convert::From;
-//! # use std::io::{Error as IOError, Write};
-//! # use std::string::FromUtf8Error;
-//! #
-//! # use orgize::export::{html::Escape, DefaultHtmlHandler, HtmlHandler};
-//! # use orgize::{Element, Org};
-//! # use slugify::slugify;
-//! #
+//! use std::convert::From;
+//! use std::io::{Error as IOError, Write};
+//! use std::string::FromUtf8Error;
+//!
+//! use orgize::export::{html::Escape, DefaultHtmlHandler, HtmlHandler};
+//! use orgize::{Element, Org};
+//! use slugify::slugify;
+//!
 //! #[derive(Debug)]
 //! enum MyError {
 //!     IO(IOError),
@@ -151,23 +140,13 @@
 //! }
 //!
 //! fn main() -> Result<(), MyError> {
-//!     let contents = r"* Title 1
-//! *Section 1*
-//! ** Title 2
-//! _Section 2_
-//! * Title 3
-//! /Section 3/
-//! * Title 4
-//! =Section 4=";
-//!
 //!     let mut writer = Vec::new();
-//!     Org::parse(&contents).html(&mut writer, MyHtmlHandler)?;
+//!     Org::parse("* title\n*section*").html(&mut writer, MyHtmlHandler)?;
+//!
 //!     assert_eq!(
 //!         String::from_utf8(writer)?,
-//!         "<main><h1><a id=\"title-1\" href=\"#title-1\">Title 1</a></h1><section><p><b>Section 1</b></p></section>\
-//!          <h2><a id=\"title-2\" href=\"#title-2\">Title 2</a></h2><section><p><u>Section 2</u></p></section>\
-//!          <h1><a id=\"title-3\" href=\"#title-3\">Title 3</a></h1><section><p><i>Section 3</i></p></section>\
-//!          <h1><a id=\"title-4\" href=\"#title-4\">Title 4</a></h1><section><p><code>Section 4</code></p></section></main>"
+//!         "<main><h1><a id=\"title\" href=\"#title\">title</a></h1>\
+//!          <section><p><b>section</b></p></section></main>"
 //!     );
 //!
 //!     Ok(())
@@ -230,6 +209,7 @@
 //!
 //! MIT
 
+pub mod config;
 pub mod elements;
 pub mod export;
 pub mod iter;
@@ -237,6 +217,7 @@ pub mod org;
 #[cfg(feature = "serde")]
 mod serde;
 
+pub use config::ParseConfig;
 pub use elements::Element;
 pub use iter::{Event, Iter};
 pub use org::Org;
diff --git a/src/org.rs b/src/org.rs
index b31f342..5ed9c83 100644
--- a/src/org.rs
+++ b/src/org.rs
@@ -3,6 +3,7 @@ use jetscii::bytes;
 use memchr::{memchr, memchr_iter};
 use std::io::{Error, Write};
 
+use crate::config::ParseConfig;
 use crate::elements::*;
 use crate::export::{DefaultHtmlHandler, HtmlHandler};
 use crate::iter::Iter;
@@ -28,7 +29,27 @@ impl<'a> Org<'a> {
             document,
             text,
         };
-        org.parse_internal();
+
+        org.parse_internal(ParseConfig::default());
+
+        org
+    }
+
+    pub fn parse_with_config(text: &'a str, config: ParseConfig<'_>) -> Self {
+        let mut arena = Arena::new();
+        let document = arena.new_node(Element::Document {
+            begin: 0,
+            end: text.len(),
+            contents_begin: 0,
+            contents_end: text.len(),
+        });
+
+        let mut org = Org {
+            arena,
+            document,
+            text,
+        };
+        org.parse_internal(config);
 
         org
     }
@@ -62,7 +83,7 @@ impl<'a> Org<'a> {
         self.html(wrtier, DefaultHtmlHandler)
     }
 
-    fn parse_internal(&mut self) {
+    fn parse_internal(&mut self, config: ParseConfig<'_>) {
         let mut node = self.document;
         loop {
             match self.arena[node].data {
@@ -92,7 +113,7 @@ impl<'a> Org<'a> {
                         }
                     }
                     while begin < end {
-                        let (headline, off, end) = Headline::parse(&self.text[begin..end], &[]);
+                        let (headline, off, end) = Headline::parse(&self.text[begin..end], &config);
                         let headline = Element::Headline {
                             headline,
                             begin,