diff options
| -rw-r--r-- | readme.txt | 148 | ||||
| -rw-r--r-- | src/main.rs | 2 |
2 files changed, 149 insertions, 1 deletions
diff --git a/readme.txt b/readme.txt new file mode 100644 index 0000000..c2bcdea --- /dev/null +++ b/readme.txt | |||
| @@ -0,0 +1,148 @@ | |||
| 1 | tbsp - tree-based source-processing language | ||
| 2 | |||
| 3 | |||
| 4 | tbsp is an awk-like language that operates on tree-sitter | ||
| 5 | syntax trees. to motivate the need for such a program, we | ||
| 6 | could begin by writing a markdown-to-html converter using | ||
| 7 | tbsp and tree-sitter-md [0]. we need some markdown to begin | ||
| 8 | with: | ||
| 9 | |||
| 10 | |||
| 11 | # 1 heading | ||
| 12 | |||
| 13 | content of first paragraph | ||
| 14 | |||
| 15 | ## 1.1 heading | ||
| 16 | |||
| 17 | content of nested paragraph | ||
| 18 | |||
| 19 | |||
| 20 | for future reference, this markdown is parsed like so by | ||
| 21 | tree-sitter-md (visualization generated by tree-viz [1]): | ||
| 22 | |||
| 23 | |||
| 24 | document | ||
| 25 | | section | ||
| 26 | | | atx_heading | ||
| 27 | | | | atx_h1_marker "#" | ||
| 28 | | | | heading_content inline "1 heading" | ||
| 29 | | | paragraph | ||
| 30 | | | | inline "content of first paragraph" | ||
| 31 | | | section | ||
| 32 | | | | atx_heading | ||
| 33 | | | | | atx_h2_marker "##" | ||
| 34 | | | | | heading_content inline "1.1 heading" | ||
| 35 | | | | paragraph | ||
| 36 | | | | | inline "content of nested paragraph" | ||
| 37 | |||
| 38 | |||
| 39 | onto the converter itself. every tbsp program is written as | ||
| 40 | a collection of stanzas. typically, we start with a stanza | ||
| 41 | like so: | ||
| 42 | |||
| 43 | |||
| 44 | BEGIN { | ||
| 45 | int depth = 0; | ||
| 46 | |||
| 47 | print("<html>\n"); | ||
| 48 | print("<body>\n"); | ||
| 49 | } | ||
| 50 | |||
| 51 | |||
| 52 | the stanza begins with a "pattern", in this case, "BEGIN", | ||
| 53 | and is followed a block of code. this block specifically, is | ||
| 54 | executed right at the beginning, before traversing the parse | ||
| 55 | tree. in this stanza, we set a "depth" variable to keep | ||
| 56 | track of nesting of markdown headers, and begin our html | ||
| 57 | document by printing the "<html>" and "<body>" tags. | ||
| 58 | |||
| 59 | we can follow this stanza with an "END" stanza, that is | ||
| 60 | executed after the traversal: | ||
| 61 | |||
| 62 | |||
| 63 | END { | ||
| 64 | print("</body>\n"); | ||
| 65 | print("</html>\n"); | ||
| 66 | } | ||
| 67 | |||
| 68 | |||
| 69 | in this stanza, we close off the tags we opened at the start | ||
| 70 | of the document. we can move onto the interesting bits of | ||
| 71 | the conversion now: | ||
| 72 | |||
| 73 | |||
| 74 | enter section { | ||
| 75 | depth += 1; | ||
| 76 | } | ||
| 77 | leave section { | ||
| 78 | depth -= 1; | ||
| 79 | } | ||
| 80 | |||
| 81 | |||
| 82 | the above stanzas begin with "enter" and "leave" clauses, | ||
| 83 | followed by the name of a tree-sitter node kind: "section". | ||
| 84 | the "section" identifier is visible in the | ||
| 85 | tree-visualization above, it encompasses a markdown-section, | ||
| 86 | and is created for every markdown header. to understand how | ||
| 87 | tbsp executes above stanzas: | ||
| 88 | |||
| 89 | |||
| 90 | document ... depth = 0 | ||
| 91 | | section <-------- enter section (1) ... depth = 1 | ||
| 92 | | | atx_heading | ||
| 93 | | | | inline | ||
| 94 | | | paragraph | ||
| 95 | | | | inline | ||
| 96 | | | section <----- enter section (2) ... depth = 2 | ||
| 97 | | | | atx_heading | ||
| 98 | | | | | inline | ||
| 99 | | | | paragraph | ||
| 100 | | | | | inline | ||
| 101 | | | | <----------- leave section (2) ... depth = 1 | ||
| 102 | | | <-------------- leave section (1) ... depth = 0 | ||
| 103 | |||
| 104 | |||
| 105 | the following stanzas should be self-explanatory now: | ||
| 106 | |||
| 107 | |||
| 108 | enter atx_heading { | ||
| 109 | print("<h"); | ||
| 110 | print(depth); | ||
| 111 | print(">"); | ||
| 112 | } | ||
| 113 | leave atx_heading { | ||
| 114 | print("</h"); | ||
| 115 | print(depth); | ||
| 116 | print(">\n"); | ||
| 117 | } | ||
| 118 | |||
| 119 | enter inline { | ||
| 120 | print(text(node)); | ||
| 121 | } | ||
| 122 | |||
| 123 | |||
| 124 | but an explanation is included nonetheless: | ||
| 125 | |||
| 126 | |||
| 127 | document ... depth = 0 | ||
| 128 | | section <-------- enter section (1) ... depth = 1 | ||
| 129 | | | atx_heading <- enter atx_heading ... print "<h1>" | ||
| 130 | | | | inline <--- enter inline ... print .. | ||
| 131 | | | | <----------- leave atx_heading ... print "</h1>" | ||
| 132 | | | paragraph | ||
| 133 | | | | inline <--- enter inline ... print .. | ||
| 134 | | | section <----- enter section (2) ... depth = 2 | ||
| 135 | | | | atx_heading enter atx_heading ... print "<h2>" | ||
| 136 | | | | | inline <- enter inline ... print .. | ||
| 137 | | | | | <-------- leave atx_heading ... print "</h2>" | ||
| 138 | | | | paragraph | ||
| 139 | | | | | inline <- enter inline ... print .. | ||
| 140 | | | | <----------- leave section (2) ... depth = 1 | ||
| 141 | | | <-------------- leave section (1) ... depth = 0 | ||
| 142 | |||
| 143 | |||
| 144 | the examples directory contains a complete markdown-to-html | ||
| 145 | converter, along with a few other motivating examples. | ||
| 146 | |||
| 147 | [0]: https://github.com/tree-sitter-grammars/tree-sitter-markdown | ||
| 148 | [1]: https://git.peppe.rs/languages/scope-tools/tree/tree-viz | ||
diff --git a/src/main.rs b/src/main.rs index ed024fc..8f63ca2 100644 --- a/src/main.rs +++ b/src/main.rs | |||
| @@ -1,7 +1,7 @@ | |||
| 1 | /// tree-based source processor | 1 | /// tree-based source processor |
| 2 | #[derive(argh::FromArgs)] | 2 | #[derive(argh::FromArgs)] |
| 3 | struct Cli { | 3 | struct Cli { |
| 4 | /// read the TBSP program source from a file | 4 | /// read the tbsp program source from a file |
| 5 | #[argh(option, short = 'f')] | 5 | #[argh(option, short = 'f')] |
| 6 | program_file: std::path::PathBuf, | 6 | program_file: std::path::PathBuf, |
| 7 | 7 | ||