Suppressable errors config

README.md

@@ -30,12 +30,34 @@ Current limitations:
 ### Errors
 
 Errors marked with a `⌫` can be suppressed using the [`--suppress`](#--suppress) option.
+Use the error name without the `HBE_PARSE_` prefix.
+
+#### `HBE_PARSE_MALFORMED_ENTITY` ⌫
+
+It's an error if the sequence of characters following an ampersand (`&`) does not form a valid entity.
+
+Technically, entities must be of one of the following forms:
+
+- `&name;`, where *name* is a reference to a valid HTML entity
+- `&nnnn;`, where *nnnn* is a Unicode code point in base 10
+- `&#xhhhh;`, where *hhhh* is a Unicode code point in base 16
+
+A malformed entity is an ampersand not followed by a sequence of characters that matches one of the above forms. This includes when the semicolon is missing, and bare ampersands (i.e. followed by whitespace or as the last character).
+
+Note that this is different from `HBE_PARSE_INVALID_ENTITY`, which is when a well-formed entity references a non-existent entity or Unicode code point.
+
+An ampersand by itself is not *necessarily* an invalid entity. However, HTML parsers and browsers may have different interpretations of bare ampersands, so it's a good idea to always use the encoded form (`&`).
+
+When this error is suppressed, malformed entities are outputted untouched.
 
 #### `HBE_PARSE_INVALID_ENTITY` ⌫
 
 It's an error if an invalid HTML entity is detected.
-If suppressed, invalid entities are simply interpreted literally.
+
+If suppressed, invalid entities are outputted untouched.
+
 See [entityrefs.c](src/main/c/rule/entity/entityrefs.c) for the list of entity references considered valid by hyperbuild.
+
 Valid entities that reference a Unicode code point must be between 0x0 and 0x10FFFF (inclusive).
 
 #### `HBE_PARSE_NONSTANDARD_TAG` ⌫
@@ -59,7 +81,7 @@ This means that `` ` `` and `'` are not valid quote marks.
 #### `HBE_PARSE_ILLEGAL_CHILD`
 
 It's an error if a tag is declared where it can't be a child of.
-This is a very simple check, and does not cover the comprehensive HTML rules, as they involve backtracking, tree traversal, and lots of conditionals.
+This is a very simple check, and does not cover the comprehensive HTML rules, which involve backtracking, tree traversal, and lots of conditionals.
 
 This rule is enforced in four parts:
 [whitelistparents.c](src/main/c/rule/relation/whitelistparents.c),
@@ -110,7 +132,7 @@ This applies even when the output is `stdout`.
 
 Suppress errors specified by this option. hyperbuild will quitely ignore and continue processing when otherwise one of the provided errors would occur.
 
-Separate the error names with commas. Suppressible errors are marked with a `⌫` in the [Errors](#errors) section.
+Omit the `HBE_PARSE_` prefix. Separate the error names with commas. Suppressible errors are marked with a `⌫` in the [Errors](#errors) section.
 
 ## Processing
 

src/main/c/error/error.c

@@ -25,13 +25,15 @@ typedef enum hbe_errcode {
   HBE_CLI_TOO_MANY_OPTIONS = 17,
   HBE_CLI_INVALID_TAG_SET,
   HBE_CLI_INVALID_TAG,
+  HBE_CLI_INVALID_SUPPRESSABLE_ERROR,
 
   HBE_IO_FOPEN_FAIL = 33,
   HBE_IO_FCLOSE_FAIL,
   HBE_IO_FREAD_FAIL,
   HBE_IO_FWRITE_FAIL,
 
-  HBE_PARSE_INVALID_ENTITY = 65,
+  HBE_PARSE_MALFORMED_ENTITY = 65,
+  HBE_PARSE_INVALID_ENTITY,
   HBE_PARSE_NONSTANDARD_TAG,
   HBE_PARSE_UCASE_TAG,
   HBE_PARSE_UCASE_ATTR,

src/main/c/main.c

@@ -8,6 +8,7 @@
 #include "rule/init.c"
 
 #include "ext/nicehash/set/str.h"
+#include "ext/nicehash/set/int32.h"
 #include "datastructure/list/buffer.h"
 
 #include "util/fstreamin.c"
@@ -77,6 +78,33 @@ static nh_set_str_t _parse_list_of_tags(char *argv) {
   return set;
 }
 
+static void _parse_and_add_errors_to_suppress(nh_set_int32_t suppressed_errors, char *argv) {
+  if (argv == NULL) {
+    return;
+  }
+
+  hb_bufferlist_t list = hb_bufferlist_create_from_split((hb_char_t *) argv, ',');
+
+  for (size_t i = 0; i < list->length; i++) {
+    hbu_buffer_t part = hb_bufferlist_get(list, i);
+    hb_char_t *part_c = hbu_buffer_underlying(part);
+
+    if (hbu_buffer_compare_lit(part, "MALFORMED_ENTITY")) {
+      nh_set_int32_add(suppressed_errors, HBE_PARSE_MALFORMED_ENTITY);
+    } else if (hbu_buffer_compare_lit(part, "INVALID_ENTITY")) {
+      nh_set_int32_add(suppressed_errors, HBE_PARSE_INVALID_ENTITY);
+    } else if (hbu_buffer_compare_lit(part, "NONSTANDARD_TAG")) {
+      nh_set_int32_add(suppressed_errors, HBE_PARSE_NONSTANDARD_TAG);
+    } else if (hbu_buffer_compare_lit(part, "UCASE_TAG")) {
+      nh_set_int32_add(suppressed_errors, HBE_PARSE_UCASE_TAG);
+    } else if (hbu_buffer_compare_lit(part, "UNQUOTED_ATTR")) {
+      nh_set_int32_add(suppressed_errors, HBE_PARSE_UNQUOTED_ATTR);
+    } else {
+      hbe_fatal(HBE_CLI_INVALID_SUPPRESSABLE_ERROR, "Unrecognised suppressable error `%s`", part);
+    }
+  }
+}
+
 int main(int argc, char **argv) {
   // Set up rules
   hbr_init();
@@ -96,6 +124,7 @@ int main(int argc, char **argv) {
       {"verbose", no_argument, NULL, 'v'},
       {"input", required_argument, NULL, 'i'},
       {"output", required_argument, NULL, 'o'},
+      {"suppress", optional_argument, NULL, 's'},
 
       {"MXcollapseWhitespace", optional_argument, NULL, 1},
       {"MXdestroyWholeWhitespace", optional_argument, NULL, 2},
@@ -113,7 +142,7 @@ int main(int argc, char **argv) {
     };
 
     int option_index = 0;
-    int c = getopt_long(argc, argv, "kbvi:o:", long_options, &option_index);
+    int c = getopt_long(argc, argv, "kbvi:o:s:", long_options, &option_index);
 
     if (c == -1) {
       if (optind != argc) {
@@ -143,6 +172,10 @@ int main(int argc, char **argv) {
       hbe_info_toggle(1);
       break;
 
+    case 's':
+      _parse_and_add_errors_to_suppress(&(config_stream->suppressed_errors), optarg);
+      break;
+
     case 1:
       config_stream->ex_collapse_whitespace = _parse_list_of_tags(optarg);
       break;

src/main/c/stream/streamoptions.c

@@ -4,11 +4,13 @@
 #include "../error/error.c"
 #include "../util/hbchar.h"
 #include "../ext/nicehash/set/str.h"
+#include "../ext/nicehash/set/int32.h"
 
 typedef struct hbs_options_s {
-  nh_set_str_t ex_collapse_whitespace; // Could be NULL to represent the universal set (i.e. don't enable)
-  nh_set_str_t ex_destroy_whole_whitespace; // Could be NULL to represent the universal set (i.e. don't enable)
-  nh_set_str_t ex_trim_whitespace; // Could be NULL to represent the universal set (i.e. don't enable)
+  nh_set_str_t ex_collapse_whitespace; // Could be NULL to represent the universal set (i.e. don't minify)
+  nh_set_str_t ex_destroy_whole_whitespace; // Could be NULL to represent the universal set (i.e. don't minify)
+  nh_set_str_t ex_trim_whitespace; // Could be NULL to represent the universal set (i.e. don't minify)
+  nh_set_int32_t suppressed_errors;
   int trim_class_attr;
   int decode_entities;
   int min_conditional_comments;
@@ -45,6 +47,7 @@ hbs_options_t hbs_options_create(void) {
   opt->ex_collapse_whitespace = _hbs_options_default_ex_collapse_whitespace();
   opt->ex_destroy_whole_whitespace = _hbs_options_default_ex_destroy_whole_whitespace();
   opt->ex_trim_whitespace = _hbs_options_default_ex_trim_whitespace();
+  opt->suppressed_errors = nh_set_int32_create();
   opt->trim_class_attr = 1;
   opt->decode_entities = 1;
   opt->min_conditional_comments = 1;