From e39478bbbd833babcff066bb639a08b4cb337695 Mon Sep 17 00:00:00 2001
From: Kragen Javier Sitaker <xentrac@special-circumstanc.es>
Date: Thu, 8 Jul 2021 00:54:13 -0300
Subject: [PATCH] Make PDF trailer parsing lazy
This facilitates exploring PDF files that I can't actually parse yet;
I can still use the Pdf object to look at parts of the file. For example:
>>> d = pdf.read('../Descargas/dercuano.20191230.pdf')
>>> d.trailer
Traceback (most recent call last):
...
File "/home/compu/izodparse/izodparse/pdf.py", line 202, in <lambda>
parenstring.xform = lambda d: ('str', bytes(d[0][1])) # XXX croaks on anything with \()
TypeError: 'tuple' object cannot be interpreted as an integer
>>> d.get_indirect_obj(440)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/compu/izodparse/izodparse/pdf.py", line 290, in get_indirect_obj
offset, plumb = result
TypeError: cannot unpack non-iterable NoneType object
>>> d.xrefs
<izodparse.pdf.XrefSection object at 0x7feaef606a30>
>>> d.xrefs[440]
b'0000095363 00000 n\r\n'
>>> d.xrefs.offset_of(440)
95363
>>> d.read(_)
b'440 0 obj\r\n<< /Border [ 0 0 .1 ] /C [ .6 .6 1 ] /Contents (notes'
In this case there are two separate problems: I need to fix
paren-string parsing for the trailer, and I need to be able to read
fractions to read the .6.
---
izodparse/ok.py | 8 --------
izodparse/pdf.py | 17 +++++++++++++----
izodparse/peg.py | 23 ++---------------------
izodparse/util.py | 24 ++++++++++++++++++++++++
plans.org | 7 +++++--
5 files changed, 44 insertions(+), 35 deletions(-)
delete mode 100644 izodparse/ok.py
create mode 100644 izodparse/util.py
diff --git a/izodparse/ok.py b/izodparse/ok.py
deleted file mode 100644
index ee91646..0000000
--- a/izodparse/ok.py
+++ /dev/null
@@ -1,8 +0,0 @@
-"Testing utilities."
-
-def ok(a, b): assert a == b, (a, b)
-
-def please_be(a, b):
- if a != b:
- raise ValueError(a, '!=', b)
-
diff --git a/izodparse/pdf.py b/izodparse/pdf.py
index 71b1e56..1d81799 100755
--- a/izodparse/pdf.py
+++ b/izodparse/pdf.py
@@ -148,7 +148,7 @@ import zlib
from . import peg
from .peg import Any, Charset, Lit, Thunk, Parse
-from .ok import ok
+from .util import ok, memoprop
### PDF and PostScript and CMap parsing ###
@@ -265,9 +265,18 @@ class Pdf:
self.xref_start = int(blob[sx:].split()[1])
# XXX there could be many sections
self.xrefs = XrefSection(self, self.xref_start)
- self.trailer_plumbing = self.parse(self.xrefs.end, drop_ws(b'trailer') + dictionary)
- self.trailer = porcelainize(self, self.trailer_plumbing[1][1])
- self.catalog = self.trailer['Root']
+
+ @memoprop
+ def trailer_plumbing(self):
+ return self.parse(self.xrefs.end, drop_ws(b'trailer') + dictionary)
+
+ @memoprop
+ def trailer(self):
+ return porcelainize(self, self.trailer_plumbing[1][1])
+
+ @memoprop
+ def catalog(self):
+ return self.trailer['Root']
def read(self, offset, size=64):
return self.blob[offset:offset+size]
diff --git a/izodparse/peg.py b/izodparse/peg.py
index 42cfaa3..5e4889c 100644
--- a/izodparse/peg.py
+++ b/izodparse/peg.py
@@ -1,5 +1,5 @@
#!/usr/bin/python3
-r"""A small PEG parser generator.
+r"""Packrat parsing engine with predictive lookahead parsing.
Too slow to use in practice (30 kilobytes/sec), but hopefully
validates our understanding of the problem and communicates it more
@@ -28,28 +28,9 @@ along with izodparse. If not, see <http://www.gnu.org/licenses/>.
"""
import types
-from .ok import ok, please_be
+from .util import ok, please_be, memoprop
-class memoprop:
- """"Simplified, non-multithreaded version of functools.cached_property.
-
- For Pythons earlier than 3.8. Doesn't support __slots__, custom
- __dict__, etc.
-
- """
- def __init__(self, func):
- self.func = func
-
- def __get__(self, instance, cls):
- cache = instance.__dict__
- if self not in cache:
- cache[self] = self.func(instance)
- return cache[self]
-
-
-### Packrat parsing engine with predictive lookahead parsing ###
-
# First, some debugging utilities:
def represent_cset(cs):
"Debugging helper for understanding first sets; takes a set() of ints or chars."
diff --git a/izodparse/util.py b/izodparse/util.py
new file mode 100644
index 0000000..7613208
--- /dev/null
+++ b/izodparse/util.py
@@ -0,0 +1,24 @@
+"Some basic utilities for testing and lazy evaluation."
+
+def ok(a, b): assert a == b, (a, b)
+
+def please_be(a, b):
+ if a != b:
+ raise ValueError(a, '!=', b)
+
+class memoprop:
+ """"Simplified, non-multithreaded version of functools.cached_property.
+
+ For Pythons earlier than 3.8. Doesn't support __slots__, custom
+ __dict__, etc.
+
+ """
+ def __init__(self, func):
+ self.func = func
+
+ def __get__(self, instance, cls):
+ cache = instance.__dict__
+ if self not in cache:
+ cache[self] = self.func(instance)
+ return cache[self]
+
diff --git a/plans.org b/plans.org
index 9eedac7..94a8419 100644
--- a/plans.org
+++ b/plans.org
@@ -1,4 +1,4 @@
-* things I am thinking of doing [3/14]
+* things I am thinking of doing [4/15]
** DONE split out pdftour into separate repo.
charpy? (too popular) rebound? (too popular) schmidtconcrete? (ok)
sclerometer? (wrong test) izod? (seems okay) 1zod or iz0d? better.
@@ -73,7 +73,10 @@ This file has a bunch of stuff in it about my local machine config.
** DONE make izodparse an installable Python package
Man, I forgot all about the distutils/setuptools mess.
** DONE split out parsing-engine stuff from PDF/PS stuff
-** TODO make xrefs, etc., lazy properties
+** DONE make trailer lazy
+This way I can open, for example, Dercuano, even though I can't parse
+its trailer yet.
+** TODO add PDF support for fractions
** TODO examine example PDF file with compressed object streams and no fonts in page resource dictionaries [0/3]
*** TODO find it
*** TODO copy it
--
GitLab