From cb7219a1528ab4df28a7e35ac5110dc01d649164 Mon Sep 17 00:00:00 2001 From: Ari Sosnovsky Date: Tue, 20 Oct 2020 19:42:37 -0400 Subject: [PATCH] better error naming --- pdfmajor/parser/__init__.py | 8 ++++---- pdfmajor/parser/exceptions.py | 13 +++++++++++++ pdfmajor/parser/objects/indirect.py | 8 ++++---- 3 files changed, 21 insertions(+), 8 deletions(-) diff --git a/pdfmajor/parser/__init__.py b/pdfmajor/parser/__init__.py index 6eae44b..71e692b 100644 --- a/pdfmajor/parser/__init__.py +++ b/pdfmajor/parser/__init__.py @@ -14,7 +14,7 @@ from pdfmajor.lexer.token import ( from .state import ParsingState from .parsers import attempt_parse_prim, deal_with_collection_object -from .exceptions import ParserError +from .exceptions import InvalidKeywordPos, ParserError from .objects.base import PDFObject from .objects.collections import PDFArray, PDFDictionary @@ -85,7 +85,7 @@ class PDFParser: if isinstance(last_ctx, IndirectObject): yield last_ctx.clone() elif self.strict: - raise ParserError(f"Invalid position for 'endobj' {token}") + raise InvalidKeywordPos(token) elif token.value == b"stream": last_ctx = self.state.current_context if last_ctx is not None and isinstance(last_ctx, IndirectObject): @@ -101,9 +101,9 @@ class PDFParser: elif token.value == b"endstream": stream = self.state.context_stack.pop() if not isinstance(stream, PDFStream): - raise ParserError(f"Invalid position for 'endstream' {token}") + raise InvalidKeywordPos(token) else: - raise ParserError(f"Invalud Keyword {token}") + raise InvalidKeywordPos(token) elif isinstance(token, TokenArray): for obj in self.state.flush_int_collections(): yield obj diff --git a/pdfmajor/parser/exceptions.py b/pdfmajor/parser/exceptions.py index e572271..dfc2d7d 100644 --- a/pdfmajor/parser/exceptions.py +++ b/pdfmajor/parser/exceptions.py @@ -1,3 +1,4 @@ +from pdfmajor.lexer.token import TokenKeyword from pdfmajor.exceptions import PDFMajorException @@ -5,6 +6,18 @@ class ParserError(PDFMajorException): pass +class InvalidKeywordPos(ParserError): + def __init__(self, token: TokenKeyword) -> None: + self.token = token + super().__init__( + f"keyword '{token.value}' was found at {token.start_loc}:{token.end_loc}" + ) + + +class InvalidIndirectObjAccess(ParserError): + pass + + class DecodeFailed(ParserError): pass diff --git a/pdfmajor/parser/objects/indirect.py b/pdfmajor/parser/objects/indirect.py index d217a53..54314e9 100644 --- a/pdfmajor/parser/objects/indirect.py +++ b/pdfmajor/parser/objects/indirect.py @@ -1,5 +1,5 @@ from typing import Dict, Tuple -from ..exceptions import ParserError +from ..exceptions import InvalidIndirectObjAccess, ParserError from .base import PDFContextualObject, PDFObject from .primitives import PDFNull @@ -63,7 +63,7 @@ class IndirectObject(PDFContextualObject): def save_object(self, obj: PDFObject): if self.__read_only: - raise ParserError( + raise InvalidIndirectObjAccess( f"attempted to override a read-only reference of an object {obj}" ) self.__col.objs[(self.obj_num, self.gen_num)] = obj @@ -76,7 +76,7 @@ class IndirectObject(PDFContextualObject): def pass_item(self, item: PDFObject): if self.__read_only: - raise ParserError( + raise InvalidIndirectObjAccess( f"attempted to add to an read-only reference of an object {item}" ) cur_obj = self.get_object() @@ -85,4 +85,4 @@ class IndirectObject(PDFContextualObject): elif isinstance(cur_obj, PDFNull): self.save_object(item) else: - raise ParserError(f"Invalid redefinition of an object {item}") + raise InvalidIndirectObjAccess(f"Invalid redefinition of an object {item}")