refactor: attempt to reuse grammar and lexer for simple tags.

customcommander · Jun 28, 2020 · 4d4629e · 4d4629e
1 parent 2c398e5
commit 4d4629e
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 26 deletions.
diff --git a/grammar.js b/grammar.js
@@ -41,7 +41,7 @@ function id(x) { return x[0]; }
     {"name": "OTHER_TAG$subexpression$1", "symbols": ["AUTHOR2"]},
     {"name": "OTHER_TAG$subexpression$1", "symbols": ["AUTHOR3"]},
     {"name": "OTHER_TAG$subexpression$1", "symbols": ["AUTHOR4"]},
-    {"name": "OTHER_TAG$subexpression$1", "symbols": ["SINGLE_LINE_ENTRY"]},
+    {"name": "OTHER_TAG$subexpression$1", "symbols": ["TAG_ENTRY"]},
     {"name": "OTHER_TAG", "symbols": ["OTHER_TAG$subexpression$1"], "postprocess": ([[d]]) => d},
     {"name": "ABSTRACT", "symbols": [(lexer.has("AB") ? {type: "AB"} : AB), (lexer.has("SEP") ? {type: "SEP"} : SEP), (lexer.has("CONTENT") ? {type: "CONTENT"} : CONTENT), "__"], "postprocess": ([,,{value}]) => ({key: 'abstract'      , value})},
     {"name": "AUTHOR_ADDR", "symbols": [(lexer.has("AD") ? {type: "AD"} : AD), (lexer.has("SEP") ? {type: "SEP"} : SEP), (lexer.has("CONTENT") ? {type: "CONTENT"} : CONTENT), "__"], "postprocess": ([,,{value}]) => ({key: 'author_address', value})},
@@ -60,15 +60,7 @@ function id(x) { return x[0]; }
     {"name": "AUTHOR2", "symbols": [(lexer.has("A2") ? {type: "A2"} : A2), (lexer.has("SEP") ? {type: "SEP"} : SEP), (lexer.has("NAME_CONTENT") ? {type: "NAME_CONTENT"} : NAME_CONTENT), "__"], "postprocess": ([,,{value}]) => ({key: 'author_sec'    , value})},
     {"name": "AUTHOR3", "symbols": [(lexer.has("A3") ? {type: "A3"} : A3), (lexer.has("SEP") ? {type: "SEP"} : SEP), (lexer.has("NAME_CONTENT") ? {type: "NAME_CONTENT"} : NAME_CONTENT), "__"], "postprocess": ([,,{value}]) => ({key: 'author_ter'    , value})},
     {"name": "AUTHOR4", "symbols": [(lexer.has("A4") ? {type: "A4"} : A4), (lexer.has("SEP") ? {type: "SEP"} : SEP), (lexer.has("NAME_CONTENT") ? {type: "NAME_CONTENT"} : NAME_CONTENT), "__"], "postprocess": ([,,{value}]) => ({key: 'author_sub'    , value})},
-    {"name": "BT_ENTRY", "symbols": [(lexer.has("BT") ? {type: "BT"} : BT), (lexer.has("SEP") ? {type: "SEP"} : SEP), (lexer.has("CONTENT") ? {type: "CONTENT"} : CONTENT), "__"], "postprocess": ([,,{value}]) => ({key: 'bt'            , value})},
-    {"name": "SINGLE_LINE_ENTRY$subexpression$1", "symbols": [(lexer.has("BT") ? {type: "BT"} : BT)]},
-    {"name": "SINGLE_LINE_ENTRY$subexpression$1", "symbols": [(lexer.has("CP") ? {type: "CP"} : CP)]},
-    {"name": "SINGLE_LINE_ENTRY$subexpression$1", "symbols": [(lexer.has("CT") ? {type: "CT"} : CT)]},
-    {"name": "SINGLE_LINE_ENTRY$subexpression$1", "symbols": [(lexer.has("ED") ? {type: "ED"} : ED)]},
-    {"name": "SINGLE_LINE_ENTRY$subexpression$1", "symbols": [(lexer.has("EP") ? {type: "EP"} : EP)]},
-    {"name": "SINGLE_LINE_ENTRY$subexpression$1", "symbols": [(lexer.has("ID") ? {type: "ID"} : ID)]},
-    {"name": "SINGLE_LINE_ENTRY$subexpression$1", "symbols": [(lexer.has("IS") ? {type: "IS"} : IS)]},
-    {"name": "SINGLE_LINE_ENTRY", "symbols": ["SINGLE_LINE_ENTRY$subexpression$1", (lexer.has("SEP") ? {type: "SEP"} : SEP), (lexer.has("CONTENT") ? {type: "CONTENT"} : CONTENT), "__"], "postprocess": ([[{value: key}],,{value}]) => ({key, value})},
+    {"name": "TAG_ENTRY", "symbols": [(lexer.has("TAG") ? {type: "TAG"} : TAG), (lexer.has("SEP") ? {type: "SEP"} : SEP), (lexer.has("CONTENT") ? {type: "CONTENT"} : CONTENT), "__"], "postprocess": ([tag,,content]) => ({key: tag.value, value: content.value})},
     {"name": "KEYWORD$ebnf$1", "symbols": ["LINE"]},
     {"name": "KEYWORD$ebnf$1", "symbols": ["KEYWORD$ebnf$1", "LINE"], "postprocess": function arrpush(d) {return d[0].concat([d[1]]);}},
     {"name": "KEYWORD", "symbols": [(lexer.has("KW") ? {type: "KW"} : KW), (lexer.has("SEP") ? {type: "SEP"} : SEP), "KEYWORD$ebnf$1"], "postprocess":  ([,,lines]) =>

diff --git a/grammar.ne b/grammar.ne
@@ -35,7 +35,7 @@ OTHER_TAG   ->  ( KEYWORD
                 | AUTHOR2
                 | AUTHOR3
                 | AUTHOR4
-                | SINGLE_LINE_ENTRY
+                | TAG_ENTRY
                 )
                 {% ([[d]]) => d %}
 
@@ -56,15 +56,8 @@ AUTHOR1     ->  %AU %SEP %NAME_CONTENT __ {% ([,,{value}]) => ({key: 'author'
 AUTHOR2     ->  %A2 %SEP %NAME_CONTENT __ {% ([,,{value}]) => ({key: 'author_sec'    , value}) %}
 AUTHOR3     ->  %A3 %SEP %NAME_CONTENT __ {% ([,,{value}]) => ({key: 'author_ter'    , value}) %}
 AUTHOR4     ->  %A4 %SEP %NAME_CONTENT __ {% ([,,{value}]) => ({key: 'author_sub'    , value}) %}
-BT_ENTRY    ->  %BT %SEP %CONTENT __      {% ([,,{value}]) => ({key: 'bt'            , value}) %}
-
-SINGLE_LINE_ENTRY ->
-  (%BT | %CP | %CT | %ED | %EP | %ID | %IS)
-  %SEP
-  %CONTENT __
-  {% ([[{value: key}],,{value}]) => ({key, value}) %}
-
 
+TAG_ENTRY -> %TAG %SEP %CONTENT __ {% ([tag,,content]) => ({key: tag.value, value: content.value}) %}
 
 KEYWORD     ->  %KW %SEP LINE:+
                 {% ([,,lines]) =>

diff --git a/lexer.js b/lexer.js
@@ -39,7 +39,6 @@ const lexer =
       , A3: /A3(?=  - )/
       , A4: /A4(?=  - )/
       , AV: /AV(?=  - )/
-      , BT: /BT(?=  - )/
       , C1: /C1(?=  - )/
       , C2: /C2(?=  - )/
       , C3: /C3(?=  - )/
@@ -50,24 +49,19 @@ const lexer =
       , C8: /C8(?=  - )/
       , CA: /CA(?=  - )/
       , CN: /CN(?=  - )/
-      , CP: /CP(?=  - )/
-      , CT: /CT(?=  - )/
       , CY: /CY(?=  - )/
       , DA: /DA(?=  - )/
       , DB: /DB(?=  - )/
       , DO: /DO(?=  - )/
       , DP: /DP(?=  - )/
-      , ED: /ED(?=  - )/
-      , EP: /EP(?=  - )/
       , ET: /ET(?=  - )/
-      , ID: /ID(?=  - )/
-      , IS: /IS(?=  - )/
       , J2: /J2(?=  - )/
       , KW: /KW(?=  - )/
       , PY: /PY(?=  - )/
       , RP: /RP(?=  - )/
       , UR: /UR(?=  - )/
       , ER: /ER(?=  - )/
+      , TAG: /(?:BT|CP|CT|ED|EP|ID|IS)(?=  - )/
       /* <<< */
       , TY_VAL: [ "ABST"   , "ADVS"  , "AGGR"
                 , "ANCIENT", "ART"   , "BILL"