octoleo/qpdf
2
1
Fork 0
mirror of https://github.com/qpdf/qpdf.git synced 2024-05-29 00:10:54 +00:00
Code Issues Releases Wiki Activity

Add state st_string_escape in QPDFTokenizer

Browse Source
This commit is contained in:
m-holger 2022-08-20 12:01:49 +01:00
parent 7c5778f999
commit 7c32f6cc2e
2 changed files with 55 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
include/qpdf/QPDFTokenizer.hh
View File

@ -203,6 +203,7 @@ class QPDFTokenizer
st_in_space,
st_in_comment,
st_in_string,
st_string_escape,
st_char_code,
st_string_after_cr,
st_lt,
@ -238,7 +239,6 @@ class QPDFTokenizer
// State for strings
int string_depth;
char bs_num_register[4];
bool last_char_was_bs;
};
#endif // QPDFTOKENIZER_HH

104
libqpdf/QPDFTokenizer.cc
View File

@ -85,7 +85,6 @@ QPDFTokenizer::reset()
char_to_unread = '\0';
inline_image_bytes = 0;
string_depth = 0;
last_char_was_bs = false;
}
QPDFTokenizer::Token::Token(token_type_e type, std::string const& value) :
@ -244,7 +243,6 @@ QPDFTokenizer::handleCharacter(char ch)
case '(':
this->string_depth = 1;
memset(this->bs_num_register, '\0', sizeof(this->bs_num_register));
this->last_char_was_bs = false;
this->state = st_in_string;
return;
@ -348,22 +346,66 @@ QPDFTokenizer::handleCharacter(char ch)
return;
case st_in_string:
{
inString(ch);
this->last_char_was_bs =
((!this->last_char_was_bs) && (ch == '\\'));
}
inString(ch);
return;
case (st_string_after_cr):
case st_string_after_cr:
// CR LF in strings are either ignored or normalized to CR
this->state = st_in_string;
if (ch != '\n') {
handleCharacter(ch);
inString(ch);
}
return;
case (st_char_code):
case st_string_escape:
this->state = st_in_string;
switch (ch) {
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
this->state = st_char_code;
inCharCode(ch);
return;
case 'n':
this->val += '\n';
return;
case 'r':
this->val += '\r';
return;
case 't':
this->val += '\t';
return;
case 'b':
this->val += '\b';
return;
case 'f':
this->val += '\f';
return;
case '\n':
return;
case '\r':
this->state = st_string_after_cr;
return;
default:
// PDF spec says backslash is ignored before anything else
this->val += ch;
return;
}
case st_char_code:
inCharCode(ch);
return;
@ -444,47 +486,9 @@ QPDFTokenizer::inHexstring(char ch)
void
QPDFTokenizer::inString(char ch)
{
bool ch_is_octal = ((ch >= '0') && (ch <= '7'));
if (ch_is_octal && this->last_char_was_bs) {
this->state = st_char_code;
inCharCode(ch);
if (ch == '\\') {
this->state = st_string_escape;
return;
} else if (this->last_char_was_bs) {
switch (ch) {
case 'n':
this->val += '\n';
return;
case 'r':
this->val += '\r';
return;
case 't':
this->val += '\t';
return;
case 'b':
this->val += '\b';
return;
case 'f':
this->val += '\f';
return;
case '\n':
return;
case '\r':
this->state = st_string_after_cr;
return;
default:
// PDF spec says backslash is ignored before anything else
this->val += ch;
return;
}
} else if (ch == '\\') {
// last_char_was_bs is set/cleared below as appropriate
} else if (ch == '(') {
this->val += ch;
++this->string_depth;