Merge #97 only "-", "•" listitem, constrain (argument)

README.md

@@ -20,7 +20,8 @@ Overview
   - contains headings (`h1`, `h2`, `h3`, `column_heading`) because `codeblock`
     terminated by "implicit stop" (no terminating `<`) consumes blank lines, so
     `block` has no way to end.
-- `line_li` ("list item")
+- `line_li` ("listitem")
+  - lines starting with `-`/`•` (_not_ `+`/`*`) are listitems.
   - consumes lines until blank line, codeblock, or next listitem.
   - nesting is ignored: indented listitems are parsed as siblings.
 - `codeblock`:
@@ -48,7 +49,7 @@ Known issues
 - `url` doesn't handle _nested_ parens. E.g. `(https://example.com/(foo)#yay)`
 - `column_heading` currently only recognizes tilde `~` preceded by space (i.e.
   `foo ~` not `foo~`). This covers 99% of :help files.
-- `column_heading` children should be plaintext. Currently its children are parsed as `$._atom`.
+- `column_heading` children should be plaintext, but currently are parsed as `$._atom`.
 
 TODO
 ----

corpus/arguments.txt

@@ -2,8 +2,8 @@
 argument
 ================================================================================
 argument: {arg}
-argument: {arg arg}
-CTRL-R CTRL-R {register CTRL-F}
+tuple: {arg,arg}
+keycode: CTRL-R {CTRL-R} {register CTRL-F}
 list of { uri:string, name: string } tables
 
 
@@ -23,7 +23,12 @@ list of { uri:string, name: string } tables
       (word)
       (keycode)
       (argument
-        (word)))
+        (word))
+      (word)
+      (ERROR
+        (word))
+      (keycode)
+      (word))
     (line
       (word)
       (word)
@@ -71,6 +76,7 @@ argument in parentheses
 ================================================================================
 NOT an argument
 ================================================================================
+a '{' '}' block
 {foo "{bar}" `{baz}` |{baz| } {}
 foo { bar 
 { {} foo{{ foo{{{
@@ -92,11 +98,18 @@ EXTERNAL *netrw-externapp* {{{2
 (help_file
   (block
     (line
-      (argument
-        (word)
-        (ERROR
-          (word)
-          (word)))
+      (word)
+      (word)
+      (word)
+      (word)
+      (word)
+      (word)
+      (word)
+      (word))
+    (line
+      (word)
+      (ERROR
+        (word))
       (word)
       (codespan
         (word))

corpus/heading3-column_heading.txt

@@ -271,11 +271,13 @@ buffer-diagram
       (word))
     (line
       (word)
-      (word)
+      (ERROR
+        (word))
       (word))
     (line
       (word)
-      (word)
+      (ERROR
+        (word))
       (word))
     (line
       (taglink

corpus/line_block.txt

@@ -80,19 +80,19 @@ block2 text text
 ================================================================================
 listitems
 ================================================================================
-* list1.a item1
-  * - •
+- list1.a item1
+  - - •
   • word,
     !foo! ~bar. word word
     'item' line3 |foo|
-* x 'list1.a' ~/foo/bar.txt
+- x 'list1.a' ~/foo/bar.txt
 li continues
-  * {nested} here
+  - {nested} here
 
-* 'list2' item w3
-  * *nested_li* word *tag2*
-* list2 item w3
-  * nested_li-2
+• 'list2' item w3
+  - *nested_li* word *tag2*
+• list2 item w3
+  - nested_li-2
     foo
     foo
 
@@ -178,16 +178,16 @@ li continues
 listitem with codeblock
 ================================================================================
 
-* list1.a item1 >
+• list1.a item1 >
   foo
-< * list1.b item1
-* w1 w2
+< • list1.b item1
+• w1 w2
   w3 >
   code1 {
     code2
   }
-<* w1
-* w2 w3
+<• w1
+• w2 w3
     `item2` line2
     {item2} line3
 
@@ -291,3 +291,48 @@ listitems + lines without blank lines
         (argument
           (word))
         (word)))))
+
+================================================================================
+listitem tricky
+================================================================================
+
+- x - x
+
+-x -x
+
+- - x -x
+- -x - x
+- -
+
+
+--------------------------------------------------------------------------------
+
+(help_file
+  (block
+    (line_li
+      (line
+        (word)
+        (word)
+        (word))
+      (line)))
+  (block
+    (line
+      (word)
+      (word)))
+  (block
+    (line_li
+      (line
+        (word)
+        (word)
+        (word))
+      (line))
+    (line_li
+      (line
+        (word)
+        (word)
+        (word))
+      (line))
+    (line_li
+      (line
+        (word))
+      (line))))

corpus/optionlink.txt

@@ -33,7 +33,6 @@ NOT optionlink: ' or 'x
 ================================================================================
 'fillchars'
 stl		' ' or '^'	statusline
-wbr		' '		windowbar
 tricky:	' 'yes'  's foo
 
 
@@ -51,11 +50,6 @@ tricky:	' 'yes'  's foo
       (word)
       (word)
       (word))
-    (line
-      (word)
-      (word)
-      (word)
-      (word))
     (line
       (word)
       (word)
@@ -72,9 +66,8 @@ no! ','sqlKeyword'
 single-char '-' 'g' '보'
 non-ascii: '\"' '%)' '-bang' '.*\\.log' '.gitignore' '@{${\"foo\"}}'
 number: '04' 'ISO-10646-1' 'python3'
-
-	Option	  '	:help 'textwidth'
-	Regular	  /	:help /[
+Option	  '	:help 'textwidth'
+Regular	  /	:help /[
 
 
 --------------------------------------------------------------------------------
@@ -101,16 +94,13 @@ number: '04' 'ISO-10646-1' 'python3'
       (word)
       (word)
       (word)
-      (tag
-        (word)
-        (MISSING "*"))
+      (word)
+      (ERROR
+        (word))
       (word)
       (word)
       (argument
-        (word)
-        (ERROR
-          (word)
-          (word)))
+        (word))
       (word)
       (word))
     (line
@@ -119,8 +109,7 @@ number: '04' 'ISO-10646-1' 'python3'
       (word)
       (word)
       (word)
-      (word)))
-  (block
+      (word))
     (line
       (word)
       (word)

corpus/taglink.txt

@@ -150,7 +150,8 @@ Note: ":autocmd" can...
     (line
       (word)
       (word)
-      (word)
+      (ERROR
+        (word))
       (word))
     (line
       (word)

corpus/tags.txt

@@ -78,10 +78,9 @@ NOT a tag
 ================================================================================
 * bullet1
   * bullet2 bullet2
-  * bullet3
-    bullet3 bullet3
-* bullet4
 
+0 \* escaped
+0 (paren *)
 1	"*" not
 2   * 	not
 3this *not no
@@ -93,47 +92,45 @@ NOT a tag
 
 (help_file
   (block
-    (line_li
-      (line
-        (word))
-      (line))
-    (line_li
-      (line
-        (word)
-        (word))
-      (line))
-    (line_li
-      (line
-        (word))
-      (line)
-      (line
-        (word)
-        (word)))
-    (line_li
-      (line
-        (word))
-      (line)))
+    (line
+      (word)
+      (word))
+    (line
+      (word)
+      (word)
+      (word)))
   (block
     (line
       (word)
       (word)
       (word))
     (line
       (word)
-      (ERROR)
+      (word)
+      (word)
+      (word)
+      (ERROR
+        (word)))
+    (line
+      (word)
+      (word)
       (word))
     (line
       (word)
-      (tag
-        (word)
-        (MISSING "*"))
+      (word)
+      (word))
+    (line
+      (word)
+      (word)
+      (ERROR
+        (word))
       (word)))
   (block
     (line
       (word)
-      (tag
-        (word)
-        (MISSING "*"))
+      (word)
+      (ERROR
+        (word))
       (word)
       (word)
       (word))))