From 693a371efa057d700c0391caa9bbcc755058b083 Mon Sep 17 00:00:00 2001
From: Huck Boles <huck@huck.website>
Date: Fri, 2 Jun 2023 17:05:29 -0500
Subject: [PATCH] added: html minifier

---
 Cargo.lock                     | 168 ++++++++++++++++++++++++++++-----
 Cargo.toml                     |   1 +
 files/README/source/index.meta |   1 +
 src/metafile/dir/node.rs       |  19 +++-
 src/tests.rs                   |   4 +-
 5 files changed, 169 insertions(+), 24 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index 72cbf58..1f37171 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -2,6 +2,15 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "aho-corasick"
+version = "0.7.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cc936419f96fa211c1b9166887b38e5e40b19958e5b895be7c1f93adec7071ac"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "anes"
 version = "0.1.6"
@@ -154,9 +163,9 @@ dependencies = [
 
 [[package]]
 name = "clap"
-version = "4.3.0"
+version = "4.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "93aae7a4192245f70fe75dd9157fc7b4a5bf53e88d30bd4396f7d8f9284d5acc"
+checksum = "b4ed2379f8603fa2b7509891660e802b88c70a79a6427a70abb5968054de2c28"
 dependencies = [
  "clap_builder",
  "clap_derive",
@@ -165,9 +174,9 @@ dependencies = [
 
 [[package]]
 name = "clap_builder"
-version = "4.3.0"
+version = "4.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f423e341edefb78c9caba2d9c7f7687d0e72e89df3ce3394554754393ac3990"
+checksum = "72394f3339a76daf211e57d4bcb374410f3965dcc606dd0e03738c7888766980"
 dependencies = [
  "anstream",
  "anstyle",
@@ -178,14 +187,14 @@ dependencies = [
 
 [[package]]
 name = "clap_derive"
-version = "4.3.0"
+version = "4.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "191d9573962933b4027f932c600cd252ce27a8ad5979418fe78e43c07996f27b"
+checksum = "59e9ef9a08ee1c0e1f2e162121665ac45ac3783b0f897db7244ae75ad9a8f65b"
 dependencies = [
  "heck",
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.18",
 ]
 
 [[package]]
@@ -209,6 +218,12 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7"
 
+[[package]]
+name = "convert_case"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6245d59a3e82a7fc217c5828a6692dbc6dfb63a0c8c90495621f7b9d79704a0e"
+
 [[package]]
 name = "cpufeatures"
 version = "0.2.7"
@@ -307,6 +322,30 @@ dependencies = [
  "typenum",
 ]
 
+[[package]]
+name = "css-minify"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "874c6e2d19f8d4a285083b11a3241bfbe01ac3ed85f26e1e6b34888d960552bd"
+dependencies = [
+ "derive_more",
+ "indexmap",
+ "nom",
+]
+
+[[package]]
+name = "derive_more"
+version = "0.99.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fb810d30a7c1953f91334de7244731fc3f3c10d7fe163338a35b9f640960321"
+dependencies = [
+ "convert_case",
+ "proc-macro2",
+ "quote",
+ "rustc_version",
+ "syn 1.0.109",
+]
+
 [[package]]
 name = "digest"
 version = "0.10.7"
@@ -498,12 +537,15 @@ checksum = "ef53942eb7bf7ff43a617b3e2c1c4a5ecf5944a7c1bc12d7ee39bbb15e5c1519"
 
 [[package]]
 name = "log"
-version = "0.4.17"
+version = "0.4.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "abb12e687cfb44aa40f41fc3978ef76448f9b6038cad6aef4259d3c095a2382e"
-dependencies = [
- "cfg-if",
-]
+checksum = "518ef76f2f87365916b142844c16d8fefd85039bc5699050210a7778ee1cd1de"
+
+[[package]]
+name = "memchr"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2dffe52ecf27772e601905b7522cb4ef790d2cc203488bbd0e2fe85fcb74566d"
 
 [[package]]
 name = "memoffset"
@@ -516,11 +558,12 @@ dependencies = [
 
 [[package]]
 name = "metaforge"
-version = "0.1.2"
+version = "0.1.3"
 dependencies = [
- "clap 4.3.0",
+ "clap 4.3.1",
  "criterion",
  "eyre",
+ "minify-html",
  "pandoc",
  "pest",
  "pest_derive",
@@ -528,6 +571,46 @@ dependencies = [
  "thiserror",
 ]
 
+[[package]]
+name = "minify-html"
+version = "0.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc4d9147754a49e80557df835eb59e743eab1bf75410a134f55dc4b9dbb692ad"
+dependencies = [
+ "aho-corasick",
+ "css-minify",
+ "lazy_static",
+ "memchr",
+ "minify-js",
+ "rustc-hash",
+]
+
+[[package]]
+name = "minify-js"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c300f90ba1138b5c5daf5d9441dc9bdc67b808aac22cf638362a2647bc213be4"
+dependencies = [
+ "lazy_static",
+ "parse-js",
+]
+
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+
 [[package]]
 name = "num-traits"
 version = "0.2.15"
@@ -549,9 +632,9 @@ dependencies = [
 
 [[package]]
 name = "once_cell"
-version = "1.17.1"
+version = "1.17.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b7e5500299e16ebb147ae15a00a942af264cf3688f47923b8fc2cd5858f23ad3"
+checksum = "9670a07f94779e00908f3e686eab508878ebb390ba6e604d3a284c00e8d0487b"
 
 [[package]]
 name = "oorandom"
@@ -574,6 +657,17 @@ dependencies = [
  "itertools 0.8.2",
 ]
 
+[[package]]
+name = "parse-js"
+version = "0.10.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "30534759e6ad87aa144c396544747e1c25b1020bd133356fd758c8facec764e5"
+dependencies = [
+ "aho-corasick",
+ "lazy_static",
+ "memchr",
+]
+
 [[package]]
 name = "pest"
 version = "2.6.0"
@@ -604,7 +698,7 @@ dependencies = [
  "pest_meta",
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.18",
 ]
 
 [[package]]
@@ -701,6 +795,21 @@ version = "0.7.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "436b050e76ed2903236f032a59761c1eb99e1b0aead2c257922771dab1fc8c78"
 
+[[package]]
+name = "rustc-hash"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
+
+[[package]]
+name = "rustc_version"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bfa0f585226d2e68097d4f95d113b15b83a82e819ab25717ec0590d9584ef366"
+dependencies = [
+ "semver",
+]
+
 [[package]]
 name = "rustix"
 version = "0.37.19"
@@ -736,6 +845,12 @@ version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
 
+[[package]]
+name = "semver"
+version = "1.0.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bebd363326d05ec3e2f532ab7660680f3b02130d780c299bca73469d521bc0ed"
+
 [[package]]
 name = "serde"
 version = "1.0.163"
@@ -753,7 +868,7 @@ checksum = "8c805777e3930c8883389c602315a24224bcc738b63905ef87cd1420353ea93e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.18",
 ]
 
 [[package]]
@@ -784,6 +899,17 @@ version = "0.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
 
+[[package]]
+name = "syn"
+version = "1.0.109"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b64191b275b66ffe2469e8af2c1cfe3bafa67b529ead792a6d0160888b4237"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
 [[package]]
 name = "syn"
 version = "2.0.18"
@@ -818,7 +944,7 @@ checksum = "f9456a42c5b0d803c8cd86e73dd7cc9edd429499f37a3550d286d5e86720569f"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.18",
 ]
 
 [[package]]
@@ -892,7 +1018,7 @@ dependencies = [
  "once_cell",
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.18",
  "wasm-bindgen-shared",
 ]
 
@@ -914,7 +1040,7 @@ checksum = "e128beba882dd1eb6200e1dc92ae6c5dbaa4311aa7bb211ca035779e5efc39f8"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.18",
  "wasm-bindgen-backend",
  "wasm-bindgen-shared",
 ]
diff --git a/Cargo.toml b/Cargo.toml
index e855186..30560cf 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -11,6 +11,7 @@ eyre = "0.6"
 pest = "2"
 pest_derive = "2"
 rayon = "1.7"
+minify-html = "0.11"
 
 [dev-dependencies]
 criterion = "0.4"
diff --git a/files/README/source/index.meta b/files/README/source/index.meta
index dfbb4bd..fb8a466 100644
--- a/files/README/source/index.meta
+++ b/files/README/source/index.meta
@@ -26,6 +26,7 @@ you rebuild it.
 - spaces are correctly preserved between directly adjacent substitutions
 - copy_only header directive
 - pandoc header now works on pattern files
+- html minification
 
 ## versions
 - 0.1.3: grammar update, new header directives
diff --git a/src/metafile/dir/node.rs b/src/metafile/dir/node.rs
index 5b878f4..40e3d0c 100644
--- a/src/metafile/dir/node.rs
+++ b/src/metafile/dir/node.rs
@@ -1,9 +1,26 @@
 use crate::{error::*, Options};
 use eyre::Result;
+use minify_html::{minify, Cfg};
 use std::{fs, path::PathBuf};
 
 use super::*;
 
+const HTML_CFG: Cfg = Cfg {
+    do_not_minify_doctype: false,
+    ensure_spec_compliant_unquoted_attribute_values: false,
+    keep_closing_tags: true,
+    keep_html_and_head_opening_tags: true,
+    keep_spaces_between_attributes: false,
+    keep_comments: false,
+    minify_css: true,
+    minify_css_level_1: false,
+    minify_css_level_2: true,
+    minify_css_level_3: false,
+    minify_js: true,
+    remove_bangs: true,
+    remove_processing_instructions: true,
+};
+
 impl<'a> DirNode<'a> {
     pub fn build(path: PathBuf, opts: &'a Options) -> Result<Self> {
         assert!(path.is_dir() && path.exists());
@@ -69,7 +86,7 @@ impl<'a> DirNode<'a> {
             file.merge(&self.global);
             match file.construct() {
                 Ok(str) => {
-                    fs::write(file.dest()?, str)?;
+                    fs::write(file.dest()?, minify(str.as_bytes(), &HTML_CFG))?;
                 }
                 Err(e) => {
                     // print a line to stderr about failure but continue with other files
diff --git a/src/tests.rs b/src/tests.rs
index b0086f6..8e69a06 100644
--- a/src/tests.rs
+++ b/src/tests.rs
@@ -189,12 +189,12 @@ fn test_global() -> Result<()> {
 
     assert_eq!(
         fs::read_to_string(dir.join("build/unit_tests/global/pattern.html"))?,
-        "<p>GOOD</p>\n<p>GOOD</p>\n\n"
+        "<p>GOOD</p><p>GOOD</p>"
     );
 
     assert_eq!(
         fs::read_to_string(dir.join("build/unit_tests/global/variable.html"))?,
-        "<p>GOOD GOOD</p>\n\n"
+        "<p>GOOD GOOD</p>"
     );
 
     Ok(())
-- 
2.45.2