Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[Parse] Add a new Parse library, to hold some common parsing-related …
…routines. Factor out common code from Xml and Json
- Loading branch information
1 parent
b893463
commit 389c66c
Showing
7 changed files
with
140 additions
and
124 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,11 @@ | ||
| namespace Rosella.Parse { | ||
| extern function parse_string; | ||
| extern function parse_alphanumeric; | ||
| extern function parse_number; | ||
| extern function error_unknown_char; | ||
| } | ||
|
|
||
| function __include_parse [anon,init,load] () | ||
| { | ||
| Rosella.load_bytecode_file('rosella/parse.pbc', 'load'); | ||
| } |
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,97 @@ | ||
| namespace Rosella.Parse | ||
| { | ||
| function parse_quoted(int q, string xml, var s, var b, int len) | ||
| { | ||
| var sb = new 'StringBuilder'; | ||
| while (have_more_chars(s, b)) { | ||
| int c = get_next(s, b); | ||
| if (c == q) | ||
| break; | ||
| if (c == ASCII_BACKSLASH) | ||
| c = get_next(s, b); | ||
| push(sb, chr(c)); | ||
| } | ||
| return sb; | ||
| } | ||
|
|
||
| function parse_string(int q, string _str, var s, var b, int len) | ||
| { | ||
| var sb = new 'StringBuilder'; | ||
| while(have_more_chars(s, b)) { | ||
| int c = get_next(s, b); | ||
| if (c == ASCII_BACKSLASH) { | ||
| // TODO: Deal with common C-style escapes | ||
| push(sb, "\\"); | ||
| c = get_next(s, b); | ||
| push(sb, chr(c)); | ||
| continue; | ||
| } | ||
| if (c == q) | ||
| break; | ||
| push(sb, chr(c)); | ||
| } | ||
| return sb; | ||
| } | ||
|
|
||
| function parse_alphanumeric(string _str, var s, var b, int len) | ||
| { | ||
| var sb = new 'StringBuilder'; | ||
| while(have_more_chars(s, b)) { | ||
| int c = get_next(s, b); | ||
| if (!codepoint_is_alphanumeric(c)) { | ||
| unshift_int(s, c); | ||
| break; | ||
| } | ||
| push(sb, chr(c)); | ||
| } | ||
| string result = string(sb); | ||
| return result; | ||
| } | ||
|
|
||
| function parse_number(int c, string _str, var s, var b, int len) | ||
| { | ||
| int have_e = false; | ||
| int have_dot = false; | ||
| int have_sign = false; | ||
| var sb = new 'StringBuilder'; | ||
| push(sb, codepoint_to_string(c)); | ||
| while (have_more_chars(s, b)) { | ||
| int d = get_next(s, b); | ||
| if (!have_sign && (d == ASCII_PLUS|| d == ASCII_DASH)) { | ||
| have_sign = true; | ||
| push(sb, codepoint_to_string(d)); | ||
| } | ||
| else if (codepoint_is_digit(d)) { | ||
| push(sb, codepoint_to_string(d)); | ||
| continue; | ||
| } | ||
| else if (!have_e && (d == ASCII_e || d == ASCII_E)) { | ||
| have_e = true; | ||
| have_sign = false; | ||
| push(sb, 'e'); | ||
| } | ||
| else if (!have_e && !have_dot && d == ASCII_PERIOD) { | ||
| have_dot = true; | ||
| push(sb, '.'); | ||
| } | ||
| else { | ||
| unshift_int(s, d); | ||
| break; | ||
| } | ||
| } | ||
| if (have_dot) { | ||
| float f_value = float(string(sb)); | ||
| return f_value; | ||
| } else { | ||
| int i_value = int(string(sb)); | ||
| return i_value; | ||
| } | ||
| } | ||
|
|
||
| function error_unknown_char(int c, string context, int pos) | ||
| { | ||
| if (c == ASCII_NULL) | ||
| Rosella.Error.error("Unexpected end of input while parsing %s at position %d", context, pos); | ||
| Rosella.Error.error("Unexpected token '%s' in %s at position %d", chr(c), context, pos); | ||
| } | ||
| } |
Oops, something went wrong.