intertext - npm Package Compare versions

Comparing version 1.4.3 to 1.5.0

lib/_patterns.js

@@ -17,2 +17,4 @@ // Generated by CoffeeScript 2.5.1
 
+  this./* must NOT set global flag */xmlname_re = RegExp(`[${this.xmlname_re_head.source}][${this.xmlname_re_head.source}${this.xmlname_re_tail.source}]*`, "u");
+
   this./* must NOT set global flag */mktsname_re_frontanchored = RegExp(`^[${this.xmlname_re_head.source}][${this.xmlname_re_head.source}${this.mktsname_re_tail.source}]*`, "u");
@@ -22,2 +24,4 @@
 
+  this./* must NOT set global flag */mktsname_re = RegExp(`[${this.xmlname_re_head.source}][${this.xmlname_re_head.source}${this.mktsname_re_tail.source}]*`, "u");
+
   /* must NOT set global flag */
@@ -24,0 +28,0 @@

lib/html.js

 // Generated by CoffeeScript 2.5.1
 (function() {
   'use strict';
-  var CND, Cupofjoe, DATOM, HtmlParser, MAIN, alert, assign, badge, debug, echo, excluded_content_parts, freeze, help, info, is_frozen, isa, jr, lets, log, new_datom, rpr, select, thaw, type_of, types, urge, validate, warn, whisper,
+  var CND, Cupofjoe, DATOM, GRAMMAR, LEXER, MAIN, PARSER, alert, assign, badge, debug, echo, excluded_content_parts, freeze, help, info, is_frozen, isa, jr, lets, log, new_datom, rpr, select, thaw, type_of, types, urge, validate, warn, whisper,
     indexOf = [].indexOf;
@@ -53,4 +53,2 @@
   //...........................................................................................................
-  HtmlParser = require('atlas-html-stream');
-
   ({Cupofjoe} = require('cupofjoe'));
@@ -62,2 +60,8 @@
 
+  LEXER = require('./chevrotain-html/chevrotain-lexer');
+
+  PARSER = require('./chevrotain-html/chevrotain-parser');
+
+  GRAMMAR = require('./chevrotain-html/chevrotain-grammar');
+
   //===========================================================================================================
@@ -226,14 +230,2 @@
 
-  // #-----------------------------------------------------------------------------------------------------------
-  // @datoms_as_nlhtml = ( ds... ) ->
-  //   R = ''
-  //   for d in ds.flat Infinity
-  //     html    = @_html_from_datoms d
-  //     sigil   = d.$key[ 0 ]
-  //     tagname = d.$key[ 1 .. ]
-  //     R      += '\n' if sigil is '<' and isa._intertext_html_block_level_tagname tagname
-  //     R      += html
-  //     # R      += '\n' if
-  //   return R
-
   //-----------------------------------------------------------------------------------------------------------
@@ -248,3 +240,3 @@ this.html_from_datoms = function(...ds) {
         d = ref[i];
-        results.push(this._html_from_datoms(d));
+        results.push(this._html_from_datom(d));
       }
@@ -255,2 +247,3 @@ return results;
 
+  /* TAINT ^^^ ??? ^^^ */
   this.$html_from_datoms = function() {
@@ -262,3 +255,3 @@ var $;
       if (!isa.list(d)) {
-        return send(this._html_from_datoms(d));
+        return send(this._html_from_datom(d));
       }
@@ -275,8 +268,8 @@ ref = this.html_from_datoms(...d);
   //-----------------------------------------------------------------------------------------------------------
-  this._html_from_datoms = function(d) {
+  this._html_from_datom = function(d) {
     var atxt, i, is_empty_tag, key, len, ref, ref1, ref2, ref3, sigil, slash, src, tagname, value, x_key, x_sys_key;
     if (isa.text(d)) {
-      return this._html_from_datoms((this.text(d))[0]);
+      return this._html_from_datom((this.text(d))[0]);
     }
-    DATOM.types.validate.datom_datom(d);
+    /* TAINT ??? */    DATOM.types.validate.datom_datom(d);
     atxt = '';
@@ -435,77 +428,25 @@ sigil = d.$key[0];
   //-----------------------------------------------------------------------------------------------------------
-  // @new_parse_method = ( settings ) ->
-  //   validate.parse_html_settings settings = { types.defaults.parse_html_settings..., settings..., }
-  this._new_parse_method = function(settings) {
-    /* NOTE strangely, throwing an error from inside the `data` handler seems to throw off the parser;
-     even when both `parser.flushText()` and `parser.reset()` were called prior to throwing the error, all
-     subsequent parsing calls will return empty lists. We therefore construct a new parser instance for
-     each call to `datoms_from_html()`. */
-    var R, parser;
-    R = null;
-    parser = new HtmlParser({
-      preserveWS: true
-    });
-    //.........................................................................................................
-    parser.on('data', ({name, data, text}) => {
-      var $value, has_keys, is_empty_tag, key, sigil, value;
-      if (name != null) {
-        name = name.toLowerCase();
+  this.datoms_from_html = function(html, settings) {
+    var R, defaults, parsification, tokenization;
+    defaults = {
+      lexer_mode: 'outside_mode',
+      parser_start: 'document'
+    };
+    settings = {...defaults, ...settings};
+    tokenization = LEXER.tokenize(html, settings.lexer_mode);
+    parsification = PARSER.parse(tokenization, settings.parser_start);
+    R = {
+      source: html,
+      cst: parsification.cst,
+      lexer_mode: settings.lexer_mode,
+      parser_start: settings.parser_start,
+      errors: {
+        lexer: tokenization.errors,
+        parser: parsification.errors
       }
-      //.......................................................................................................
-      if (name === '!doctype') {
-        $value = 'html';
-        for (key in data) {
-          $value = key;
-          break;
-        }
-        return R.push(new_datom('^doctype', $value));
-      }
-      if (text != null) {
-        //.......................................................................................................
-        return R.push(new_datom('^text', {text}));
-      }
-      is_empty_tag = isa._intertext_html_empty_element_tagname(name);
-      // debug '^7787^', { name, data, text, is_empty_tag, }
-      if (data == null) {
-        if (is_empty_tag) {
-          return;
-        }
-        // throw new Error "^intertext/_new_parse_method@6069^ found closing tag, but HTML5 <#{name}> is an empty tag"
-        return R.push(new_datom('>' + name));
-      }
-      has_keys = false;
-      for (key in data) {
-        value = data[key];
-        has_keys = true;
-        if (value === '') {
-          data[key] = true;
-        }
-      }
-      sigil = is_empty_tag ? '^' : '<';
-      if (!has_keys) {
-        return R.push(new_datom(sigil + name));
-      }
-      return R.push(new_datom(sigil + name, data));
-    });
-    parser.on('error', function(error) {
-      throw error;
-    });
-    // parser.on 'end', -> R.push new_datom '^stop'
-    //.........................................................................................................
-    return (html) => {
-      // urge '^7787^', jr html
-      R = [];
-      parser.write(html);
-      parser.flushText();
-      // parser.reset()      # call if parser is to be reused
-      return R;
     };
+    return GRAMMAR.extract_tokens(R);
   };
 
   //-----------------------------------------------------------------------------------------------------------
-  this.datoms_from_html = function(html) {
-    return this._new_parse_method()(html);
-  };
-
-  //-----------------------------------------------------------------------------------------------------------
   this.$datoms_from_html = function() {
@@ -512,0 +453,0 @@ var $;

lib/main.js

 // Generated by CoffeeScript 2.5.1
 (function() {
   'use strict';
-  var CND, FS, Html, Hyph, INTERTEXT, Intertext, MAIN, Mkts, Multimix, PATH, Patterns, Slabs, Tbl, alert, assign, badge, cast, debug, echo, help, info, isa, jr, log, rpr, type_of, urge, validate, warn, whisper;
+  var CND, FS, Html, Hyph, INTERTEXT, Intertext, MAIN, Mkts, Multimix, PATH, Patterns, Slabs, Tbl, alert, assign, badge, cast, debug, echo, help, info, inspect, isa, jr, log, rpr, type_of, urge, validate, warn, whisper;
 
@@ -46,2 +46,4 @@ //###########################################################################################################
 
+  ({inspect} = require('util'));
+
   Html = (function() {
@@ -119,2 +121,16 @@ /*
 
+  //-----------------------------------------------------------------------------------------------------------
+  this.rpr = function(...P) {
+    var x;
+    return ((function() {
+      var i, len, results;
+      results = [];
+      for (i = 0, len = P.length; i < len; i++) {
+        x = P[i];
+        results.push(inspect(x, this.rpr_settings));
+      }
+      return results;
+    }).call(this)).join(' ');
+  };
+
   //===========================================================================================================
@@ -138,2 +154,8 @@
         this.TBL = new Tbl();
+        this.rpr_settings = {
+          depth: 2e308,
+          maxArrayLength: 2e308,
+          breakLength: 2e308,
+          compact: true
+        };
         if (target != null) {
@@ -140,0 +162,0 @@ this.export(target);

lib/tabulate.js

@@ -0,1 +1,2 @@
+// Generated by CoffeeScript 2.5.1
 (function() {
@@ -505,1 +506,3 @@ //###########################################################################################################
 }).call(this);
+
+//# sourceMappingURL=tabulate.js.map

lib/tests/tabulate.test.js

@@ -0,1 +1,2 @@
+// Generated by CoffeeScript 2.5.1
 (function() {
@@ -719,1 +720,3 @@ 'use strict';
 }).call(this);
+
+//# sourceMappingURL=tabulate.test.js.map

package.json

 {
   "name": "intertext",
-  "version": "1.4.3",
+  "version": "1.5.0",
   "description": "Services for Recurrent Text-related Tasks",
@@ -33,2 +33,3 @@ "main": "lib/main.js",
     "atlas-html-stream": "^1.2.0",
+    "chevrotain": "^6.5.0",
     "cnd": "^5.3.0",
@@ -35,0 +36,0 @@ "cupofjoe": "0.0.4",

README-html.md

@@ -70,5 +70,22 @@
 
+* InterText HTML uses the most generous definition of an XML name, ever. It basically allows anything except
+  those few characters that would definitely mess with the rest of the grammar, so tags like `<123>`,
+  `<foo:bar#baz.gnu bro:go=42>` are totally OK. Consumers are advised to do their own checking to narrow
+  down available choices or interpret special constructs, as the case may be. A valid InterText HTML name is
+  any sequence of one or more characters, excluding only
+  * whitespace,
+  * brackets (`{[(<>)]}`),
+  * question and exclamation marks (`!?`),
+  * slashes (`/`),
+  * equal signs (`=`),
+  * and quotes (`'` and `"`).
 
+* Special constructs are not further analyzed ATM; this includes
+  * Doctypes (e.g. `<!DOCTYPE html>`),
+  * XML declarations (e.g. `<?xml foo bar?>`),
+  * Processing Instructions (e.g. `<?what ever?>`).
+  Observe that tag-like constructs that start with `<?` (left pointy bracket, question mark) but end with a
+  plain `>` (right pointy bracket) not preceded by a `?` (question mark) are considered ungrammatical (they
+  are be allowed in SGML, though).
 
-
 ### HTML Parsing
@@ -75,0 +92,0 @@

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

879976

increased by27.84%

Number of package files

66

increased by29.41%

Lines of code

6936

increased by19.52%

Worsened metrics

Dependency count

12

increased by9.09%

Dependency changes

• + Addedchevrotain@^6.5.0

• + Addedchevrotain@6.5.0(transitive)

• + Addedregexp-to-ast@0.4.0(transitive)