core
/
oga
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Use 4 spaces for C/Java code.

This commit is contained in:
Yorick Peterse 2014-05-06 09:41:36 +02:00
parent 4e2dca2fd9
commit d2742cfdde
2 changed files with 134 additions and 128 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
.editorconfig
View File

@ -8,5 +8,11 @@ trim_trailing_whitespace = true
[*.{y,rb,rl}] [*.{y,rb,rl}]
indent_size = 2 indent_size = 2
[*.{h,h},ext/oga/xml/*.rl] [*.{h,c,java}]
indent_size = 2 indent_size = 4
[ext/liboga/*.rl]
indent_size = 4
[ext/liboga/org/liboga/xml/*.rl]
indent_size = 4

252
ext/liboga/lexer.rl
View File

@ -14,17 +14,17 @@ VALUE oga_cLexer;
* liboga_xml_lexer_callback(self, "on_string", encoding, ts, te); * liboga_xml_lexer_callback(self, "on_string", encoding, ts, te);
*/ */
void liboga_xml_lexer_callback( void liboga_xml_lexer_callback(
VALUE self, VALUE self,
const char *name, const char *name,
rb_encoding *encoding, rb_encoding *encoding,
const char *ts, const char *ts,
const char *te const char *te
) )
{ {
VALUE value = rb_enc_str_new(ts, te - ts, encoding); VALUE value = rb_enc_str_new(ts, te - ts, encoding);
VALUE method = rb_intern(name); VALUE method = rb_intern(name);
rb_funcall(self, method, 1, value); rb_funcall(self, method, 1, value);
} }
/** /**
@ -36,9 +36,9 @@ void liboga_xml_lexer_callback(
*/ */
void liboga_xml_lexer_callback_simple(VALUE self, const char *name) void liboga_xml_lexer_callback_simple(VALUE self, const char *name)
{ {
VALUE method = rb_intern(name); VALUE method = rb_intern(name);
rb_funcall(self, method, 0); rb_funcall(self, method, 0);
} }
%% write data; %% write data;
@ -55,33 +55,33 @@ void liboga_xml_lexer_callback_simple(VALUE self, const char *name)
*/ */
VALUE oga_xml_lexer_advance(VALUE self) VALUE oga_xml_lexer_advance(VALUE self)
{ {
/* Pull the data in from Ruby land. */ /* Pull the data in from Ruby land. */
VALUE data_ivar = rb_ivar_get(self, rb_intern("@data")); VALUE data_ivar = rb_ivar_get(self, rb_intern("@data"));
/* Make sure that all data passed back to Ruby has the proper encoding. */ /* Make sure that all data passed back to Ruby has the proper encoding. */
rb_encoding *encoding = rb_enc_get(data_ivar); rb_encoding *encoding = rb_enc_get(data_ivar);
char *data_str_val = StringValuePtr(data_ivar); char *data_str_val = StringValuePtr(data_ivar);
const char *p = data_str_val; const char *p = data_str_val;
const char *pe = data_str_val + strlen(data_str_val); const char *pe = data_str_val + strlen(data_str_val);
const char *eof = pe; const char *eof = pe;
const char *ts, *te; const char *ts, *te;
int act = 0; int act = 0;
int cs = 0; int cs = 0;
int top = 0; int top = 0;
/* /*
Fixed stack size is enough since the lexer doesn't use that many nested Fixed stack size is enough since the lexer doesn't use that many nested
fcalls. fcalls.
*/ */
int stack[8]; int stack[8];
%% write init; %% write init;
%% write exec; %% write exec;
return Qnil; return Qnil;
} }
%%{ %%{
@ -99,20 +99,20 @@ VALUE oga_xml_lexer_advance(VALUE self)
# Machine for processing double quoted strings. # Machine for processing double quoted strings.
string_dquote := |* string_dquote := |*
^dquote+ => { ^dquote+ => {
liboga_xml_lexer_callback(self, "on_string", encoding, ts, te); liboga_xml_lexer_callback(self, "on_string", encoding, ts, te);
}; };
dquote => { fret; }; dquote => { fret; };
*|; *|;
# Machine for processing single quoted strings. # Machine for processing single quoted strings.
string_squote := |* string_squote := |*
^squote+ => { ^squote+ => {
liboga_xml_lexer_callback(self, "on_string", encoding, ts, te); liboga_xml_lexer_callback(self, "on_string", encoding, ts, te);
}; };
squote => { fret; }; squote => { fret; };
*|; *|;
# DOCTYPES # DOCTYPES
@ -128,33 +128,33 @@ VALUE oga_xml_lexer_advance(VALUE self)
doctype_start = '<!DOCTYPE'i whitespace+; doctype_start = '<!DOCTYPE'i whitespace+;
action start_doctype { action start_doctype {
liboga_xml_lexer_callback_simple(self, "on_start_doctype"); liboga_xml_lexer_callback_simple(self, "on_start_doctype");
fcall doctype; fcall doctype;
} }
# Machine for processing doctypes. Doctype values such as the public # Machine for processing doctypes. Doctype values such as the public
# and system IDs are treated as T_STRING tokens. # and system IDs are treated as T_STRING tokens.
doctype := |* doctype := |*
'PUBLIC' | 'SYSTEM' => { 'PUBLIC' | 'SYSTEM' => {
liboga_xml_lexer_callback(self, "on_doctype_type", encoding, ts, te); liboga_xml_lexer_callback(self, "on_doctype_type", encoding, ts, te);
}; };
# Lex the public/system IDs as regular strings. # Lex the public/system IDs as regular strings.
dquote => { fcall string_dquote; }; dquote => { fcall string_dquote; };
squote => { fcall string_squote; }; squote => { fcall string_squote; };
# Whitespace inside doctypes is ignored since there's no point in # Whitespace inside doctypes is ignored since there's no point in
# including it. # including it.
whitespace; whitespace;
identifier => { identifier => {
liboga_xml_lexer_callback(self, "on_doctype_name", encoding, ts, te); liboga_xml_lexer_callback(self, "on_doctype_name", encoding, ts, te);
}; };
'>' => { '>' => {
liboga_xml_lexer_callback_simple(self, "on_doctype_end"); liboga_xml_lexer_callback_simple(self, "on_doctype_end");
fret; fret;
}; };
*|; *|;
# CDATA # CDATA
@ -171,18 +171,18 @@ VALUE oga_xml_lexer_advance(VALUE self)
cdata_end = ']]>'; cdata_end = ']]>';
action start_cdata { action start_cdata {
liboga_xml_lexer_callback_simple(self, "on_cdata_start"); liboga_xml_lexer_callback_simple(self, "on_cdata_start");
fcall cdata; fcall cdata;
} }
# Machine that for processing the contents of CDATA tags. Everything # Machine that for processing the contents of CDATA tags. Everything
# inside a CDATA tag is treated as plain text. # inside a CDATA tag is treated as plain text.
cdata := |* cdata := |*
any* cdata_end => { any* cdata_end => {
liboga_xml_lexer_callback(self, "on_text", encoding, ts, te - 3); liboga_xml_lexer_callback(self, "on_text", encoding, ts, te - 3);
liboga_xml_lexer_callback_simple(self, "on_cdata_end"); liboga_xml_lexer_callback_simple(self, "on_cdata_end");
fret; fret;
}; };
*|; *|;
# Comments # Comments
@ -200,18 +200,18 @@ VALUE oga_xml_lexer_advance(VALUE self)
comment_end = '-->'; comment_end = '-->';
action start_comment { action start_comment {
liboga_xml_lexer_callback_simple(self, "on_comment_start"); liboga_xml_lexer_callback_simple(self, "on_comment_start");
fcall comment; fcall comment;
} }
# Machine used for processing the contents of a comment. Everything # Machine used for processing the contents of a comment. Everything
# inside a comment is treated as plain text (similar to CDATA tags). # inside a comment is treated as plain text (similar to CDATA tags).
comment := |* comment := |*
any* comment_end => { any* comment_end => {
liboga_xml_lexer_callback(self, "on_text", encoding, ts, te - 3); liboga_xml_lexer_callback(self, "on_text", encoding, ts, te - 3);
liboga_xml_lexer_callback_simple(self, "on_comment_end"); liboga_xml_lexer_callback_simple(self, "on_comment_end");
fret; fret;
}; };
*|; *|;
# XML declaration tags # XML declaration tags
@ -222,26 +222,26 @@ VALUE oga_xml_lexer_advance(VALUE self)
xml_decl_end = '?>'; xml_decl_end = '?>';
action start_xml_decl { action start_xml_decl {
liboga_xml_lexer_callback_simple(self, "on_xml_decl_start"); liboga_xml_lexer_callback_simple(self, "on_xml_decl_start");
fcall xml_decl; fcall xml_decl;
} }
# Machine that processes the contents of an XML declaration tag. # Machine that processes the contents of an XML declaration tag.
xml_decl := |* xml_decl := |*
xml_decl_end => { xml_decl_end => {
liboga_xml_lexer_callback_simple(self, "on_xml_decl_end"); liboga_xml_lexer_callback_simple(self, "on_xml_decl_end");
fret; fret;
}; };
# Attributes and their values (e.g. version="1.0"). # Attributes and their values (e.g. version="1.0").
identifier => { identifier => {
liboga_xml_lexer_callback(self, "on_attribute", encoding, ts, te); liboga_xml_lexer_callback(self, "on_attribute", encoding, ts, te);
}; };
dquote => { fcall string_dquote; }; dquote => { fcall string_dquote; };
squote => { fcall string_squote; }; squote => { fcall string_squote; };
any; any;
*|; *|;
# Elements # Elements
@ -253,9 +253,9 @@ VALUE oga_xml_lexer_advance(VALUE self)
# namespace (if any). Remaining work is delegated to a dedicated # namespace (if any). Remaining work is delegated to a dedicated
# machine. # machine.
action start_element { action start_element {
liboga_xml_lexer_callback(self, "on_element_start", encoding, ts + 1, te); liboga_xml_lexer_callback(self, "on_element_start", encoding, ts + 1, te);
fcall element_head; fcall element_head;
} }
element_start = '<' identifier; element_start = '<' identifier;
@ -267,62 +267,62 @@ VALUE oga_xml_lexer_advance(VALUE self)
# For example, in `<p foo="bar">` the element head is ` foo="bar"`. # For example, in `<p foo="bar">` the element head is ` foo="bar"`.
# #
element_head := |* element_head := |*
whitespace | '='; whitespace | '=';
newline => { newline => {
liboga_xml_lexer_callback_simple(self, "on_newline"); liboga_xml_lexer_callback_simple(self, "on_newline");
}; };
# Attribute names. # Attribute names.
identifier => { identifier => {
liboga_xml_lexer_callback(self, "on_attribute", encoding, ts, te); liboga_xml_lexer_callback(self, "on_attribute", encoding, ts, te);
}; };
# Attribute values. # Attribute values.
dquote => { fcall string_dquote; }; dquote => { fcall string_dquote; };
squote => { fcall string_squote; }; squote => { fcall string_squote; };
# The closing character of the open tag. # The closing character of the open tag.
('>' | '/') => { ('>' | '/') => {
fhold; fhold;
fret; fret;
}; };
*|; *|;
main := |* main := |*
element_start => start_element; element_start => start_element;
doctype_start => start_doctype; doctype_start => start_doctype;
cdata_start => start_cdata; cdata_start => start_cdata;
comment_start => start_comment; comment_start => start_comment;
xml_decl_start => start_xml_decl; xml_decl_start => start_xml_decl;
# Enter the body of the tag. If HTML mode is enabled and the current # Enter the body of the tag. If HTML mode is enabled and the current
# element is a void element we'll close it and bail out. # element is a void element we'll close it and bail out.
'>' => { '>' => {
liboga_xml_lexer_callback_simple(self, "on_element_open_end"); liboga_xml_lexer_callback_simple(self, "on_element_open_end");
}; };
# Regular closing tags. # Regular closing tags.
'</' identifier '>' => { '</' identifier '>' => {
liboga_xml_lexer_callback_simple(self, "on_element_end"); liboga_xml_lexer_callback_simple(self, "on_element_end");
}; };
# Self closing elements that are not handled by the HTML mode. # Self closing elements that are not handled by the HTML mode.
'/>' => { '/>' => {
liboga_xml_lexer_callback_simple(self, "on_element_end"); liboga_xml_lexer_callback_simple(self, "on_element_end");
}; };
# Note that this rule should be declared at the very bottom as it # Note that this rule should be declared at the very bottom as it
# will otherwise take precedence over the other rules. # will otherwise take precedence over the other rules.
^('<' | '>')+ => { ^('<' | '>')+ => {
liboga_xml_lexer_callback(self, "on_text", encoding, ts, te); liboga_xml_lexer_callback(self, "on_text", encoding, ts, te);
}; };
*|; *|;
}%% }%%
void Init_liboga_xml_lexer() void Init_liboga_xml_lexer()
{ {
oga_cLexer = rb_define_class_under(oga_mXML, "Lexer", rb_cObject); oga_cLexer = rb_define_class_under(oga_mXML, "Lexer", rb_cObject);
rb_define_method(oga_cLexer, "advance_native", oga_xml_lexer_advance, 0); rb_define_method(oga_cLexer, "advance_native", oga_xml_lexer_advance, 0);
} }