forked from
jonmsterling.com/ocaml-forester
ocaml
Merge remote-tracking branch 'origin/main'
+100
-94
+1
-3
lib/frontend/LaTeX_template.ml
+1
-3
lib/frontend/LaTeX_template.ml
···
1
1
let write fmt ~preamble ~source =
2
2
let newline () = Format.fprintf fmt "\n" in
3
-
Format.fprintf fmt {|\RequirePackage{ifpdf}|};
4
-
newline ();
5
-
Format.fprintf fmt {|\ifpdf\documentclass[crop]{standalone}\else\documentclass[crop,dvisvgm]{standalone}\fi|};
3
+
Format.fprintf fmt {|\documentclass[crop,dvisvgm]{standalone}|};
6
4
newline ();
7
5
Format.fprintf fmt "%s" preamble;
8
6
newline ();
+86
-91
lib/frontend/Lexer.mll
+86
-91
lib/frontend/Lexer.mll
···
1
1
{
2
+
open Prelude
2
3
exception SyntaxError of string
3
4
let drop_sigil c str = 1 |> List.nth @@ String.split_on_char c str
4
-
let ident str = Grammar.IDENT (drop_sigil '\\' str)
5
-
let illegal str = raise @@ SyntaxError str
6
-
7
-
let text str = Grammar.TEXT str
8
-
let whitespace str = Grammar.WHITESPACE str
9
-
let dbg str = Format.printf "%s\n" str; flush stdout
10
-
11
-
let verbatim = ref false
12
-
13
-
let return_thunk lexbuf thunk =
14
-
match !verbatim with
15
-
| true -> text (Lexing.lexeme lexbuf)
16
-
| false -> thunk ()
17
-
18
-
let return lexbuf tok =
19
-
return_thunk lexbuf @@ fun _ -> tok
20
-
5
+
let verbatim_buff = Buffer.create 1000
21
6
}
22
7
23
8
let digit = ['0'-'9']
···
25
10
let int = '-'? digit+
26
11
let ident = '\\' (alpha) (alpha|digit|'-'|'/'|'#')*
27
12
let addr = (alpha) (alpha|digit|'_'|'-')*
28
-
let whitespace = [' ' '\t']+
13
+
let wschar = [' ' '\t']
29
14
let newline = '\r' | '\n' | "\r\n"
30
15
let text = [^ ' ' '%' '#' '\\' '{' '}' '[' ']' '(' ')' '\r' '\n']+
31
16
32
17
rule token =
33
18
parse
34
-
| "\\%" { return lexbuf @@ Grammar.TEXT "%"}
19
+
| "\\%" { Grammar.TEXT "%"}
35
20
| "%" { comment lexbuf }
36
-
| "##{" { return lexbuf @@ Grammar.HASH_HASH_LBRACE }
37
-
| "#{" { return lexbuf @@ Grammar.HASH_LBRACE }
38
-
| "\\\\" { return lexbuf @@ Grammar.IDENT {|\|} }
39
-
| "\\," { return lexbuf @@ Grammar.IDENT {|,|} }
40
-
| "\\\"" { return lexbuf @@ Grammar.IDENT {|"|} }
41
-
| "\\'" { return lexbuf @@ Grammar.IDENT {|'|} }
42
-
| "\\`" { return lexbuf @@ Grammar.IDENT {|`|} }
43
-
| "\\_" { return lexbuf @@ Grammar.IDENT {|_|} }
44
-
| "\\;" { return lexbuf @@ Grammar.IDENT {|;|} }
45
-
| "\\#" { return lexbuf @@ Grammar.IDENT {|#|} }
46
-
| "\\{" { return lexbuf @@ Grammar.IDENT {|{|} }
47
-
| "\\}" { return lexbuf @@ Grammar.IDENT {|}|} }
48
-
| "\\[" { return lexbuf @@ Grammar.IDENT {|[|} }
49
-
| "\\]" { return lexbuf @@ Grammar.IDENT {|]|} }
50
-
| "\\startverb" { verbatim := true; token lexbuf }
51
-
| "\\stopverb" { verbatim := false; token lexbuf }
52
-
| "\\ " { return lexbuf @@ Grammar.IDENT {| |} }
53
-
| "\\title" { return lexbuf @@ Grammar.TITLE }
54
-
| "\\parent" { return lexbuf @@ Grammar.PARENT }
55
-
| "\\taxon" { return lexbuf @@ Grammar.TAXON }
56
-
| "\\author" { return lexbuf @@ Grammar.AUTHOR }
57
-
| "\\contributor" { return lexbuf @@ Grammar.CONTRIBUTOR }
58
-
| "\\scope" { return lexbuf @@ Grammar.SCOPE }
59
-
| "\\put" { return lexbuf @@ Grammar.PUT }
60
-
| "\\put?" { return lexbuf @@ Grammar.DEFAULT }
61
-
| "\\get" { return lexbuf @@ Grammar.GET }
62
-
| "\\tag" { return lexbuf @@ Grammar.TAG }
63
-
| "\\ref" { return lexbuf @@ Grammar.REF }
64
-
| "\\date" { return lexbuf @@ Grammar.DATE }
65
-
| "\\import" { return lexbuf @@ Grammar.IMPORT }
66
-
| "\\export" { return lexbuf @@ Grammar.EXPORT }
67
-
| "\\namespace" { return lexbuf @@ Grammar.NAMESPACE }
68
-
| "\\open" { return lexbuf @@ Grammar.OPEN }
69
-
| "\\meta" { return lexbuf @@ Grammar.META }
70
-
| "\\def" { return lexbuf @@ Grammar.DEF }
71
-
| "\\alloc" { return lexbuf @@ Grammar.ALLOC }
72
-
| "\\let" { return lexbuf @@ Grammar.LET }
73
-
| "\\tex" { return lexbuf @@ Grammar.TEX }
74
-
| "\\transclude" { return lexbuf @@ Grammar.TRANSCLUDE }
75
-
| "\\subtree" { return lexbuf @@ Grammar.SUBTREE }
76
-
| "\\query/and" {return lexbuf @@ Grammar.QUERY_AND }
77
-
| "\\query/or" {return lexbuf @@ Grammar.QUERY_OR }
78
-
| "\\query/author" {return lexbuf @@ Grammar.QUERY_AUTHOR }
79
-
| "\\query/tag" {return lexbuf @@ Grammar.QUERY_TAG }
80
-
| "\\query/taxon" {return lexbuf @@ Grammar.QUERY_TAXON }
81
-
| "\\query/meta" {return lexbuf @@ Grammar.QUERY_META }
82
-
| "\\query" { return lexbuf @@ Grammar.QUERY_TREE }
83
-
| "\\xml" { return lexbuf @@ Grammar.XML_TAG }
84
-
| "\\p" { return lexbuf @@ Grammar.PRIM `P }
85
-
| "\\em" { return lexbuf @@ Grammar.PRIM `Em }
86
-
| "\\strong" { return lexbuf @@ Grammar.PRIM `Strong }
87
-
| "\\li" { return lexbuf @@ Grammar.PRIM `Li }
88
-
| "\\ul" { return lexbuf @@ Grammar.PRIM `Ul }
89
-
| "\\ol" { return lexbuf @@ Grammar.PRIM `Ol }
90
-
| "\\code" { return lexbuf @@ Grammar.PRIM `Code }
91
-
| "\\blockquote" { return lexbuf @@ Grammar.PRIM `Blockquote }
92
-
| "\\pre" { return lexbuf @@ Grammar.PRIM `Pre }
93
-
| "\\object" { return lexbuf @@ Grammar.OBJECT }
94
-
| "\\patch" { return lexbuf @@ Grammar.PATCH }
95
-
| "\\call" { return lexbuf @@ Grammar.CALL }
96
-
| "#" { return lexbuf @@ Grammar.TEXT "#" }
97
-
| ident { return lexbuf @@ ident (Lexing.lexeme lexbuf) }
98
-
| '{' { return lexbuf @@ Grammar.LBRACE }
99
-
| '}' { return lexbuf @@ Grammar.RBRACE }
100
-
| '[' { return lexbuf @@ Grammar.LSQUARE }
101
-
| ']' { return lexbuf @@ Grammar.RSQUARE }
102
-
| '(' { return lexbuf @@ Grammar.LPAREN }
103
-
| ')' { return lexbuf @@ Grammar.RPAREN }
104
-
| text { text (Lexing.lexeme lexbuf) }
105
-
| whitespace { whitespace (Lexing.lexeme lexbuf) }
106
-
| newline { Lexing.new_line lexbuf; whitespace (Lexing.lexeme lexbuf) }
21
+
| "##{" { Grammar.HASH_HASH_LBRACE }
22
+
| "#{" { Grammar.HASH_LBRACE }
23
+
| "\\\\" { Grammar.IDENT {|\|} }
24
+
| "\\," { Grammar.IDENT {|,|} }
25
+
| "\\\"" { Grammar.IDENT {|"|} }
26
+
| "\\'" { Grammar.IDENT {|'|} }
27
+
| "\\`" { Grammar.IDENT {|`|} }
28
+
| "\\_" { Grammar.IDENT {|_|} }
29
+
| "\\;" { Grammar.IDENT {|;|} }
30
+
| "\\#" { Grammar.IDENT {|#|} }
31
+
| "\\{" { Grammar.IDENT {|{|} }
32
+
| "\\}" { Grammar.IDENT {|}|} }
33
+
| "\\[" { Grammar.IDENT {|[|} }
34
+
| "\\]" { Grammar.IDENT {|]|} }
35
+
| "\\startverb" {
36
+
Buffer.clear verbatim_buff;
37
+
verbatim lexbuf;
38
+
let text = String_util.trim_newlines @@ Buffer.contents verbatim_buff in
39
+
Grammar.TEXT text
40
+
}
41
+
| "\\ " { Grammar.IDENT {| |} }
42
+
| "\\title" { Grammar.TITLE }
43
+
| "\\parent" { Grammar.PARENT }
44
+
| "\\taxon" { Grammar.TAXON }
45
+
| "\\author" { Grammar.AUTHOR }
46
+
| "\\contributor" { Grammar.CONTRIBUTOR }
47
+
| "\\scope" { Grammar.SCOPE }
48
+
| "\\put" { Grammar.PUT }
49
+
| "\\put?" { Grammar.DEFAULT }
50
+
| "\\get" { Grammar.GET }
51
+
| "\\tag" { Grammar.TAG }
52
+
| "\\ref" { Grammar.REF }
53
+
| "\\date" { Grammar.DATE }
54
+
| "\\import" { Grammar.IMPORT }
55
+
| "\\export" { Grammar.EXPORT }
56
+
| "\\namespace" { Grammar.NAMESPACE }
57
+
| "\\open" { Grammar.OPEN }
58
+
| "\\meta" { Grammar.META }
59
+
| "\\def" { Grammar.DEF }
60
+
| "\\alloc" { Grammar.ALLOC }
61
+
| "\\let" { Grammar.LET }
62
+
| "\\tex" { Grammar.TEX }
63
+
| "\\transclude" { Grammar.TRANSCLUDE }
64
+
| "\\subtree" { Grammar.SUBTREE }
65
+
| "\\query/and" {Grammar.QUERY_AND }
66
+
| "\\query/or" {Grammar.QUERY_OR }
67
+
| "\\query/author" {Grammar.QUERY_AUTHOR }
68
+
| "\\query/tag" {Grammar.QUERY_TAG }
69
+
| "\\query/taxon" {Grammar.QUERY_TAXON }
70
+
| "\\query/meta" {Grammar.QUERY_META }
71
+
| "\\query" { Grammar.QUERY_TREE }
72
+
| "\\xml" { Grammar.XML_TAG }
73
+
| "\\p" { Grammar.PRIM `P }
74
+
| "\\em" { Grammar.PRIM `Em }
75
+
| "\\strong" { Grammar.PRIM `Strong }
76
+
| "\\li" { Grammar.PRIM `Li }
77
+
| "\\ul" { Grammar.PRIM `Ul }
78
+
| "\\ol" { Grammar.PRIM `Ol }
79
+
| "\\code" { Grammar.PRIM `Code }
80
+
| "\\blockquote" { Grammar.PRIM `Blockquote }
81
+
| "\\pre" { Grammar.PRIM `Pre }
82
+
| "\\object" { Grammar.OBJECT }
83
+
| "\\patch" { Grammar.PATCH }
84
+
| "\\call" { Grammar.CALL }
85
+
| "#" { Grammar.TEXT "#" }
86
+
| ident { Grammar.IDENT (drop_sigil '\\' (Lexing.lexeme lexbuf)) }
87
+
| '{' { Grammar.LBRACE }
88
+
| '}' { Grammar.RBRACE }
89
+
| '[' { Grammar.LSQUARE }
90
+
| ']' { Grammar.RSQUARE }
91
+
| '(' { Grammar.LPAREN }
92
+
| ')' { Grammar.RPAREN }
93
+
| text { Grammar.TEXT (Lexing.lexeme lexbuf) }
94
+
| wschar+ { Grammar.WHITESPACE (Lexing.lexeme lexbuf) }
95
+
| newline { Lexing.new_line lexbuf; Grammar.WHITESPACE (Lexing.lexeme lexbuf) }
107
96
| eof { Grammar.EOF }
108
-
| _ { illegal @@ Lexing.lexeme lexbuf }
97
+
| _ { raise @@ SyntaxError (Lexing.lexeme lexbuf) }
109
98
110
99
and comment =
111
100
parse
···
113
102
| eof { Grammar.EOF }
114
103
| _ { comment lexbuf }
115
104
105
+
and verbatim =
106
+
parse
107
+
| "\\stopverb" { () }
108
+
| _ as c
109
+
{ Buffer.add_char verbatim_buff c;
110
+
verbatim lexbuf }
+12
lib/prelude/String_util.ml
+12
lib/prelude/String_util.ml
···
17
17
let sentence_case str =
18
18
let words = String.split_on_char ' ' str in
19
19
String.concat " " @@ List.mapi title_case_word words
20
+
21
+
let trim_newlines str =
22
+
23
+
let rec process_lines lines =
24
+
match lines with
25
+
| [] -> []
26
+
| "" :: lines -> process_lines lines
27
+
| _ -> lines
28
+
in
29
+
30
+
let lines = String.split_on_char '\n' str in
31
+
String.concat "\n" @@ List.rev @@ process_lines @@ List.rev @@ process_lines lines