Using functools.partial to make custom filters for pdfquery getting attribute error

Question

Background

I'm using pdfquery to parse multiple files like this one.

Problem

I'm trying to write a generalized filer function, building off of the custom selectors mentioned in pdfquery's docs, that can take a specific range as an argument. Because this is referenced I thought I could get around this by supplying a partial function using functools.partial (as seen below)

Input

import pdfquery
import functools

def load_file(PDF_FILE):
    pdf = pdfquery.PDFQuery(PDF_FILE)
    pdf.load()
    return pdf

file_with_table = 'Path to the file mentioned above'
pdf = load_file(file_with_table)


def elements_in_range(x1_range):
    return in_range(x1_range[0], x1_range[1], float(this.get('x1',0)))

x1_part = functools.partial(elements_in_range, (95,350))

pdf.pq('LTPage[page_index="0"] *').filter(x1_part)

But when I do that I get the following attribute error;

Output

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
C:\Anaconda3\lib\site-packages\pyquery\pyquery.py in filter(self, selector)
    597                     if len(args) == 1:
--> 598                         func_globals(selector)['this'] = this
    599                     if callback(selector, i, this):

C:\Anaconda3\lib\site-packages\pyquery\pyquery.py in func_globals(f)
     28 def func_globals(f):
---> 29     return f.__globals__ if PY3k else f.func_globals
     30 

AttributeError: 'functools.partial' object has no attribute '__globals__'

During handling of the above exception, another exception occurred:

AttributeError                            Traceback (most recent call last)
<ipython-input-74-d75c2c19f74b> in <module>()
     15 x1_part = functools.partial(elements_in_range, (95,350))
     16 
---> 17 pdf.pq('LTPage[page_index="0"] *').filter(x1_part)

C:\Anaconda3\lib\site-packages\pyquery\pyquery.py in filter(self, selector)
    600                         elements.append(this)
    601             finally:
--> 602                 f_globals = func_globals(selector)
    603                 if 'this' in f_globals:
    604                     del f_globals['this']

C:\Anaconda3\lib\site-packages\pyquery\pyquery.py in func_globals(f)
     27 
     28 def func_globals(f):
---> 29     return f.__globals__ if PY3k else f.func_globals
     30 
     31 

AttributeError: 'functools.partial' object has no attribute '__globals__'

Is there any way to get around this? Or possibly some other way to write a custom selector for pdfquery that can take arguments?

Answer 1

What about just using a function to return a new function (similar to a functools.partial in a way), but using a closure instead?

import pdfquery

def load_file(PDF_FILE):
    pdf = pdfquery.PDFQuery(PDF_FILE)
    pdf.load()
    return pdf

file_with_table = './RG234621_90110.pdf'
pdf = load_file(file_with_table)

def in_range(x1, x2, sample):
    return x1 <= sample <= x2

def in_x_range(bounds):
    def wrapped(*args, **kwargs):
        x = float(this.get('x1', 0))
        return in_range(bounds[0], bounds[1], x)
    return wrapped

def in_y_range(bounds):
    def wrapped(*args, **kwargs):
        y = float(this.get('y1', 0))
        return in_range(bounds[0], bounds[1], y)
    return wrapped


print(len(pdf.pq('LTPage[page_index="0"] *').filter(in_x_range((95, 350))).filter(in_y_range((60, 100)))))

# Or, perhaps easier to read

x_check = in_x_range((95, 350))
y_check = in_y_range((60, 100))

print(len(pdf.pq('LTPage[page_index="0"] *').filter(x_check).filter(y_check)))

OUTPUT

1
16 # <-- bounds check is larger for y in this test

You could event parameterize the property you are comparing

import pdfquery

def load_file(PDF_FILE):
    pdf = pdfquery.PDFQuery(PDF_FILE)
    pdf.load()
    return pdf

file_with_table = './RG234621_90110.pdf'
pdf = load_file(file_with_table)

def in_range(prop, bounds):
    def wrapped(*args, **kwargs):
        n = float(this.get(prop, 0))
        return bounds[0] <= n <= bounds[1]
    return wrapped


print(len(pdf.pq('LTPage[page_index="0"] *').filter(in_range('x1', (95, 350))).filter(in_range('y1', (60, 100)))))

x_check = in_range('x1', (95, 350))
y_check = in_range('y1', (40, 100))

print(len(pdf.pq('LTPage[page_index="0"] *').filter(x_check).filter(y_check)))

I would also suggest the use of the parse_tree_cacher argument as that sped up the time for me to find an appropriate solution (though you may not need to reprocess frequently as I did while figuring this out).

import pdfquery
from pdfquery.cache import FileCache

def load_file(PDF_FILE):
    pdf = pdfquery.PDFQuery(PDF_FILE, parse_tree_cacher=FileCache("/tmp/"))
    pdf.load()
    return pdf