fix named entities

In 462bb0ef0ba9e027f5138c87438328db718d15da I dropped the
markup5ever::data dependency but omitted to include its
named_entities data. This commit remedies that mistake.

1 files changed, 61 insertions, 0 deletions

diff --git a/build.rs b/build.rs
new file mode 100644
index 0000000..8d4404c
--- /dev/null
+++ b/build.rs
@@ -0,0 +1,61 @@
+// Copyright 2014-2017 The html5ever Project Developers. See the
+// COPYRIGHT file at the top-level directory of this distribution.
+//
+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+extern crate phf_codegen;
+
+use std::collections::HashMap;
+use std::env;
+use std::fs::File;
+use std::io::Write;
+use std::path::Path;
+
+mod entities;
+
+fn main() {
+    named_entities_to_phf(&Path::new(&env::var("OUT_DIR").unwrap()).join("named_entities.rs"));
+}
+
+fn named_entities_to_phf(to: &Path) {
+    let mut entities: HashMap<&str, (u32, u32)> = entities::NAMED_ENTITIES
+        .iter()
+        .map(|(name, cp1, cp2)| {
+            assert!(name.starts_with('&'));
+            (&name[1..], (*cp1, *cp2))
+        })
+        .collect();
+
+    // Add every missing prefix of those keys, mapping to NULL characters.
+    for key in entities.keys().cloned().collect::<Vec<_>>() {
+        for n in 1..key.len() {
+            entities.entry(&key[..n]).or_insert((0, 0));
+        }
+    }
+    entities.insert("", (0, 0));
+
+    let mut phf_map = phf_codegen::Map::new();
+    for (key, value) in entities {
+        phf_map.entry(key, &format!("{:?}", value));
+    }
+
+    let mut file = File::create(to).unwrap();
+    writeln!(
+        &mut file,
+        r#"
+/// A map of entity names to their codepoints. The second codepoint will
+/// be 0 if the entity contains a single codepoint. Entities have their preceeding '&' removed.
+"#
+    )
+    .unwrap();
+    writeln!(
+        &mut file,
+        "pub static NAMED_ENTITIES: Map<&'static str, (u32, u32)> = {};",
+        phf_map.build(),
+    )
+    .unwrap();
+}