From 4a4eebcf86f258b3dc465400092063300a588bbf Mon Sep 17 00:00:00 2001 From: Behdad Esfahbod Date: Fri, 9 Oct 2020 21:06:20 -0600 Subject: [PATCH] [buffer/serialize] Minor renames in Ragel machines As per my previous review on: https://github.com/harfbuzz/harfbuzz/pull/2687 --- src/hb-buffer-deserialize-json.hh | 2 +- src/hb-buffer-deserialize-json.rl | 18 +++--- src/hb-buffer-deserialize-text.hh | 104 ++++++++++++++++++------------ src/hb-buffer-deserialize-text.rl | 20 ++++-- 4 files changed, 86 insertions(+), 58 deletions(-) diff --git a/src/hb-buffer-deserialize-json.hh b/src/hb-buffer-deserialize-json.hh index 14deee982..acb233e15 100644 --- a/src/hb-buffer-deserialize-json.hh +++ b/src/hb-buffer-deserialize-json.hh @@ -338,7 +338,7 @@ static const char _deserialize_json_indicies[] = { 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, 70, - 1, 71, 1, 1, 1, 1, 1, 1, + 1, 71, 72, 1, 1, 1, 1, 1, 1, 1, 1, 1, 72, 72, 1, 72, 72, 72, 72, 72, 72, 72, 72, 72, 72, 1, 1, 1, 1, 1, 1, 1, diff --git a/src/hb-buffer-deserialize-json.rl b/src/hb-buffer-deserialize-json.rl index 14e1bb429..42e4b9183 100644 --- a/src/hb-buffer-deserialize-json.rl +++ b/src/hb-buffer-deserialize-json.rl @@ -76,14 +76,14 @@ action ensure_unicode { } } -action parse_glyph { +action parse_glyph_name { if (!hb_font_glyph_from_string (font, tok, p - tok, &info.codepoint)) return false; } -action parse_gid { if (!parse_uint (tok, p, &info.codepoint)) return false; } +action parse_codepoint { if (!parse_uint (tok, p, &info.codepoint)) return false; } action parse_cluster { if (!parse_uint (tok, p, &info.cluster )) return false; } action parse_x_offset { if (!parse_int (tok, p, &pos.x_offset )) return false; } action parse_y_offset { if (!parse_int (tok, p, &pos.y_offset )) return false; } @@ -96,21 +96,21 @@ num = '-'? unum; comma = space* ',' space*; colon = space* ':' space*; -glyph_id = unum; -glyph_name = alpha (alnum|'_'|'.'|'-')*; +codepoint = unum; +glyph_name = alpha (alnum|'_'|'.'|'-'|'#')*; -glyph_string = '"' (glyph_name >tok %parse_glyph) '"'; -glyph_number = (glyph_id >tok %parse_gid); +parse_glyph_name = '"' (glyph_name >tok %parse_glyph_name) '"'; +parse_codepoint = (codepoint >tok %parse_codepoint); -glyph = "\"g\"" colon (glyph_string | glyph_number) @ensure_glyphs; -codepoint = "\"u\"" colon glyph_number @ensure_unicode; +glyph = "\"g\"" colon (parse_glyph_name | parse_codepoint) @ensure_glyphs; +unicode = "\"u\"" colon parse_codepoint @ensure_unicode; cluster = "\"cl\"" colon (unum >tok %parse_cluster); xoffset = "\"dx\"" colon (num >tok %parse_x_offset); yoffset = "\"dy\"" colon (num >tok %parse_y_offset); xadvance= "\"ax\"" colon (num >tok %parse_x_advance); yadvance= "\"ay\"" colon (num >tok %parse_y_advance); -element = glyph | codepoint | cluster | xoffset | yoffset | xadvance | yadvance; +element = glyph | unicode | cluster | xoffset | yoffset | xadvance | yadvance; item = ( '{' space* element (comma element)* space* '}') >clear_item diff --git a/src/hb-buffer-deserialize-text.hh b/src/hb-buffer-deserialize-text.hh index c43771870..10cc16053 100644 --- a/src/hb-buffer-deserialize-text.hh +++ b/src/hb-buffer-deserialize-text.hh @@ -402,24 +402,24 @@ static const char _deserialize_text_trans_targs[] = { }; static const char _deserialize_text_trans_actions[] = { - 0, 0, 0, 0, 0, 1, 2, 0, - 2, 2, 3, 3, 3, 0, 2, 2, - 2, 0, 0, 2, 2, 2, 0, 0, - 2, 2, 2, 2, 2, 0, 0, 4, - 2, 2, 2, 0, 0, 5, 0, 6, - 5, 5, 0, 0, 0, 7, 7, 7, - 0, 8, 9, 9, 9, 8, 8, 0, - 0, 10, 11, 12, 11, 11, 13, 13, - 13, 7, 14, 14, 7, 15, 16, 15, - 15, 0, 10 + 0, 0, 0, 0, 1, 0, 2, 0, + 3, 3, 4, 4, 4, 0, 3, 3, + 3, 0, 0, 3, 3, 3, 0, 0, + 3, 3, 3, 3, 3, 0, 0, 5, + 3, 3, 3, 0, 0, 6, 7, 8, + 6, 6, 0, 0, 0, 9, 9, 9, + 0, 10, 11, 11, 11, 10, 10, 0, + 0, 12, 13, 14, 13, 13, 15, 15, + 15, 9, 16, 16, 9, 17, 18, 17, + 17, 0, 12 }; static const char _deserialize_text_eof_actions[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 5, 0, 0, 0, - 7, 7, 8, 0, 0, 8, 11, 13, - 13, 11, 7, 15, 15, 7, 8 + 0, 0, 0, 0, 6, 0, 0, 0, + 9, 9, 10, 0, 0, 10, 13, 15, + 15, 13, 9, 17, 17, 9, 10 }; static const int deserialize_text_start = 1; @@ -429,7 +429,7 @@ static const int deserialize_text_error = 0; static const int deserialize_text_en_main = 1; -#line 124 "hb-buffer-deserialize-text.rl" +#line 132 "hb-buffer-deserialize-text.rl" static hb_bool_t @@ -482,13 +482,20 @@ _resume: goto _again; switch ( _deserialize_text_trans_actions[_trans] ) { - case 2: + case 1: +#line 38 "hb-buffer-deserialize-text.rl" + { + memset (&info, 0, sizeof (info)); + memset (&pos , 0, sizeof (pos )); +} + break; + case 3: #line 51 "hb-buffer-deserialize-text.rl" { tok = p; } break; - case 10: + case 12: #line 55 "hb-buffer-deserialize-text.rl" { if (unlikely (buffer->content_type != HB_BUFFER_CONTENT_TYPE_GLYPHS)) @@ -502,7 +509,21 @@ _resume: } } break; - case 9: + case 7: +#line 67 "hb-buffer-deserialize-text.rl" + { + if (unlikely (buffer->content_type != HB_BUFFER_CONTENT_TYPE_UNICODE)) + { + if (buffer->content_type != HB_BUFFER_CONTENT_TYPE_INVALID) { + buffer->clear(); + return false; + } + assert (buffer->len == 0); + buffer->content_type = HB_BUFFER_CONTENT_TYPE_UNICODE; + } +} + break; + case 11: #line 79 "hb-buffer-deserialize-text.rl" { if (!hb_font_glyph_from_string (font, @@ -511,31 +532,30 @@ _resume: return false; } break; - case 6: + case 8: #line 86 "hb-buffer-deserialize-text.rl" {if (!parse_hex (tok, p, &info.codepoint )) return false; } break; - case 14: + case 16: #line 88 "hb-buffer-deserialize-text.rl" { if (!parse_uint (tok, p, &info.cluster )) return false; } break; - case 4: + case 5: #line 89 "hb-buffer-deserialize-text.rl" { if (!parse_int (tok, p, &pos.x_offset )) return false; } break; - case 16: + case 18: #line 90 "hb-buffer-deserialize-text.rl" { if (!parse_int (tok, p, &pos.y_offset )) return false; } break; - case 12: + case 14: #line 91 "hb-buffer-deserialize-text.rl" { if (!parse_int (tok, p, &pos.x_advance)) return false; } break; - case 1: -#line 38 "hb-buffer-deserialize-text.rl" + case 2: +#line 51 "hb-buffer-deserialize-text.rl" { - memset (&info, 0, sizeof (info)); - memset (&pos , 0, sizeof (pos )); + tok = p; } #line 67 "hb-buffer-deserialize-text.rl" { @@ -550,7 +570,7 @@ _resume: } } break; - case 8: + case 10: #line 79 "hb-buffer-deserialize-text.rl" { if (!hb_font_glyph_from_string (font, @@ -567,7 +587,7 @@ _resume: *end_ptr = p; } break; - case 5: + case 6: #line 86 "hb-buffer-deserialize-text.rl" {if (!parse_hex (tok, p, &info.codepoint )) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -579,7 +599,7 @@ _resume: *end_ptr = p; } break; - case 7: + case 9: #line 88 "hb-buffer-deserialize-text.rl" { if (!parse_uint (tok, p, &info.cluster )) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -591,7 +611,7 @@ _resume: *end_ptr = p; } break; - case 15: + case 17: #line 90 "hb-buffer-deserialize-text.rl" { if (!parse_int (tok, p, &pos.y_offset )) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -603,7 +623,7 @@ _resume: *end_ptr = p; } break; - case 11: + case 13: #line 91 "hb-buffer-deserialize-text.rl" { if (!parse_int (tok, p, &pos.x_advance)) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -615,7 +635,7 @@ _resume: *end_ptr = p; } break; - case 13: + case 15: #line 92 "hb-buffer-deserialize-text.rl" { if (!parse_int (tok, p, &pos.y_advance)) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -627,7 +647,7 @@ _resume: *end_ptr = p; } break; - case 3: + case 4: #line 38 "hb-buffer-deserialize-text.rl" { memset (&info, 0, sizeof (info)); @@ -650,7 +670,7 @@ _resume: } } break; -#line 654 "hb-buffer-deserialize-text.hh" +#line 674 "hb-buffer-deserialize-text.hh" } _again: @@ -662,7 +682,7 @@ _again: if ( p == eof ) { switch ( _deserialize_text_eof_actions[cs] ) { - case 8: + case 10: #line 79 "hb-buffer-deserialize-text.rl" { if (!hb_font_glyph_from_string (font, @@ -679,7 +699,7 @@ _again: *end_ptr = p; } break; - case 5: + case 6: #line 86 "hb-buffer-deserialize-text.rl" {if (!parse_hex (tok, p, &info.codepoint )) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -691,7 +711,7 @@ _again: *end_ptr = p; } break; - case 7: + case 9: #line 88 "hb-buffer-deserialize-text.rl" { if (!parse_uint (tok, p, &info.cluster )) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -703,7 +723,7 @@ _again: *end_ptr = p; } break; - case 15: + case 17: #line 90 "hb-buffer-deserialize-text.rl" { if (!parse_int (tok, p, &pos.y_offset )) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -715,7 +735,7 @@ _again: *end_ptr = p; } break; - case 11: + case 13: #line 91 "hb-buffer-deserialize-text.rl" { if (!parse_int (tok, p, &pos.x_advance)) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -727,7 +747,7 @@ _again: *end_ptr = p; } break; - case 13: + case 15: #line 92 "hb-buffer-deserialize-text.rl" { if (!parse_int (tok, p, &pos.y_advance)) return false; } #line 43 "hb-buffer-deserialize-text.rl" @@ -739,14 +759,14 @@ _again: *end_ptr = p; } break; -#line 743 "hb-buffer-deserialize-text.hh" +#line 763 "hb-buffer-deserialize-text.hh" } } _out: {} } -#line 148 "hb-buffer-deserialize-text.rl" +#line 156 "hb-buffer-deserialize-text.rl" *end_ptr = p; diff --git a/src/hb-buffer-deserialize-text.rl b/src/hb-buffer-deserialize-text.rl index dd3e972ac..aa82e7d76 100644 --- a/src/hb-buffer-deserialize-text.rl +++ b/src/hb-buffer-deserialize-text.rl @@ -102,10 +102,7 @@ cluster = '=' (unum >tok %parse_cluster); offsets = '@' (num >tok %parse_x_offset) ',' (num >tok %parse_y_offset ); advances= '+' (num >tok %parse_x_advance) (',' (num >tok %parse_y_advance))?; -codepoint = xdigit+ >tok %parse_hexdigits; -unicode_id = 'U' '+' >clear_item @ensure_unicode codepoint cluster? %add_item; - -item = +glyph_item = ( glyph cluster? @@ -116,8 +113,19 @@ item = %add_item ; -glyphs = item (space* '|' space* item)* space* ('|'|']')?; -unicodes = unicode_id (space* '|' space* unicode_id)* space* ('|'|'>')?; +unicode = 'U' '+' xdigit+ >tok @ensure_unicode %parse_hexdigits; + +unicode_item = + ( + unicode + cluster? + ) + >clear_item + %add_item + ; + +glyphs = glyph_item (space* '|' space* glyph_item)* space* ('|'|']')?; +unicodes = unicode_item (space* '|' space* unicode_item)* space* ('|'|'>')?; main := space* ( ('[' glyphs) | ('<' unicodes) );