cleaned up parser class

This commit is contained in:
ari committed 2020-10-21 17:52:46 -04:00
1 parent 754e248aac
commit cfc2dfca47
1 file changed
+33 -21
+33 -21
View File
@@ -1,6 +1,6 @@
import io import io
from pdfmajor.parser.objects.stream import PDFStream from pdfmajor.parser.objects.stream import PDFStream
from typing import Iterator, Optional, Union from typing import Iterator, List, Optional, Union
from pdfmajor.lexer import PDFLexer from pdfmajor.lexer import PDFLexer
from pdfmajor.lexer.token import ( from pdfmajor.lexer.token import (
@@ -79,12 +79,7 @@ class PDFParser:
for token in self.lexer.iter_tokens(): for token in self.lexer.iter_tokens():
attempt_prim = attempt_parse_prim(token, self.state) attempt_prim = attempt_parse_prim(token, self.state)
if attempt_prim.success: if attempt_prim.success:
cur_ctx = self.state.current_context yield from self._feed_or_yield_objs(attempt_prim.next_objs)
for obj in attempt_prim.next_objs:
if cur_ctx is not None:
cur_ctx.pass_item(obj)
else:
yield obj
elif isinstance(token, TokenComment): elif isinstance(token, TokenComment):
yield self.state.set_last_obj( yield self.state.set_last_obj(
PDFComment( PDFComment(
@@ -94,26 +89,15 @@ class PDFParser:
) )
elif isinstance(token, TokenKeyword): elif isinstance(token, TokenKeyword):
if token.value == b"R": if token.value == b"R":
obj = self.state.get_indobjects() yield from self._on_indirect_ref_close()
cur_ctx = self.state.current_context
if cur_ctx is not None:
cur_ctx.pass_item(obj)
else:
yield obj
elif token.value == b"obj": elif token.value == b"obj":
self.state.initialize_indirect_obj() self.state.initialize_indirect_obj()
elif token.value == b"endobj": elif token.value == b"endobj":
last_ctx = self.state.context_stack.pop() yield from self._on_endobj(token)
if isinstance(last_ctx, IndirectObject):
yield last_ctx.clone()
elif self.strict:
raise InvalidKeywordPos(token)
elif token.value == b"stream": elif token.value == b"stream":
self._on_stream(token) self._on_stream(token)
elif token.value == b"endstream": elif token.value == b"endstream":
stream: PDFContextualObject = self.state.context_stack.pop() self._on_endstream(token)
if not isinstance(stream, PDFStream):
raise InvalidKeywordPos(token)
else: else:
raise InvalidKeywordPos(token) raise InvalidKeywordPos(token)
elif isinstance(token, TokenArray): elif isinstance(token, TokenArray):
@@ -131,6 +115,29 @@ class PDFParser:
strict=self.strict, strict=self.strict,
) )
def _feed_or_yield_objs(self, next_objs: List[PDFObject]):
cur_ctx = self.state.current_context
for obj in next_objs:
if cur_ctx is not None:
cur_ctx.pass_item(obj)
else:
yield obj
def _on_indirect_ref_close(self):
obj = self.state.get_indobjects()
cur_ctx = self.state.current_context
if cur_ctx is not None:
cur_ctx.pass_item(obj)
else:
yield obj
def _on_endobj(self, token: TokenKeyword):
last_ctx = self.state.context_stack.pop()
if isinstance(last_ctx, IndirectObject):
yield last_ctx.clone()
elif self.strict:
raise InvalidKeywordPos(token)
def _on_stream(self, token: TokenKeyword): def _on_stream(self, token: TokenKeyword):
last_ctx = self.state.current_context last_ctx = self.state.current_context
if last_ctx is not None and isinstance(last_ctx, IndirectObject): if last_ctx is not None and isinstance(last_ctx, IndirectObject):
@@ -141,3 +148,8 @@ class PDFParser:
self.lexer.seek(stream.offset + stream.length) self.lexer.seek(stream.offset + stream.length)
else: else:
raise ParserError(f"PDFStream is missing initilization dictionary") raise ParserError(f"PDFStream is missing initilization dictionary")
def _on_endstream(self, token: TokenKeyword):
stream: PDFContextualObject = self.state.context_stack.pop()
if not isinstance(stream, PDFStream):
raise InvalidKeywordPos(token)