Stephen Karl Larroque lrq3000

PDF Testing Gist

These two files, pdf_linkchecker.py and pdf_fontchecker.py are code examples to go along with a blog article: http://reachtim.com/articles/PDF-Testing.html

See the article for details on how to test your PDFs for broken internal and external links and for unembedded fonts.

This simple script will take a picture of a whiteboard and use parts of the ImageMagick library with sane defaults to clean it up tremendously.

The script is here:

#!/bin/bash
convert "$1" -morphology Convolve DoG:15,100,0 -negate -normalize -blur 0x1 -channel RBG -level 60%,91%,0.1 "$2"

People

	import collections

	def dict_merge(dct, merge_dct):
	""" Recursive dict merge. Inspired by :meth:``dict.update()``, instead of
	updating only top-level keys, dict_merge recurses down into dicts nested
	to an arbitrary depth, updating keys. The ``merge_dct`` is merged into
	``dct``.

	:param dct: dict onto which the merge is executed
	:param merge_dct: dct merged into dct

	"""
	This creates the following GIF, where the text appears to be "embedded"
	in the video and "disappears" behind rapunzel.

	http://i.imgur.com/gxEHfLX.gif
	"""

	from moviepy.editor import *
	import numpy as np
	import skimage.morphology as skm

	# By Jake VanderPlas
	# License: BSD-style

	import matplotlib.pyplot as plt
	import numpy as np


	def discrete_cmap(N, base_cmap=None):
	"""Create an N-bin discrete colormap from the specified input map"""

	time 1.6452050209 --- d4 = d1.copy(); d4.update(d2), d4.update(d3)
	time 1.69228887558 --- d4 = dict(d1, **d2); d4.update(d3)
	time 1.78650903702 --- d4 = {}; d4.update(d1); d4.update(d2), d4.update(d3)
	time 1.92449307442 --- d4 = {} for d in (d1, d2, d3): d4.update(d)
	time 2.00036215782 --- d4 = dict(d1, d2); d5=dict(d4, d3)
	time 2.04427695274 --- d4 = dict(d1) for d in (d2, d3): d4.update(d)
	time 2.68033099174 --- d4 = reduce(lambda x,y: dict(x, **y), (d1, d2, d3))
	time 3.72226691246 --- d4 = dict(chain(*[d.iteritems() for d in (d1, d2, d3)]))
	time 4.01872420311 --- d4 = dict(d1.items() + d2.items() + d3.items())
	time 4.07779598236 --- d4 = dict(chain.from_iterable(d.iteritems() for d in (d1, d2, d3)))

	"""A simple implementation of a greedy transition-based parser. Released under BSD license."""
	from os import path
	import os
	import sys
	from collections import defaultdict
	import random
	import time
	import pickle

	SHIFT = 0; RIGHT = 1; LEFT = 2;

	$files = ls -Recurse \| where {!$_.PsIsContainer}
	$files \| foreach {
	$destinationFolder = $_.Directory.FullName -replace "SrcFolderName", "SrcFolderName_converted"
	emf2sf.bat $_.FullName --out-dir $destinationFolder
	if($LastExitCode -eq 2)
	{
	copy $_.FullName $destinationFolder
	}
	}

	# Place the following in your home directory at ~/.numpy-site.cfg
	# in order to install numpy with openblas support


	[openblas]
	libraries = openblas
	library_dirs = /usr/local/opt/openblas/lib
	include_dirs = /usr/local/opt/openblas/include