File: test_writepdf.py

package info (click to toggle)
pyth 0.5.6-3
  • links: PTS, VCS
  • area: main
  • in suites: wheezy
  • size: 312 kB
  • sloc: python: 1,609; makefile: 7
file content (96 lines) | stat: -rw-r--r-- 2,856 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
"""
unit tests of the pdf writer
"""

import unittest
import subprocess
import tempfile
import os
import sys
import BeautifulSoup

from pyth.plugins.pdf.writer import PDFWriter
from pyth.plugins.python.reader import *


class TestWritePDF(unittest.TestCase):

    def pdf_to_html(self, pdf):
        """
        We are using pdftohtml to convert the pdf document to an html
        document.

        Since it is difficult to check a pdf document, this allow us
        to first convert it into html, and then perform the checks on
        this html document.
        """
        # pdftohtml needs its input from a file so we first save the
        # pdf into a temporary file.
        _, filename = tempfile.mkstemp(suffix='.pdf')
        file = open(filename, "wb")
        try:
            file.write(pdf)
            file.close()
            command = ["pdftohtml", "-stdout", filename]
            try:
                proc = subprocess.Popen(command, stdout=subprocess.PIPE)
            except OSError:
                print "Make sure that pdftohtml is installed"
                raise
            ret = proc.communicate()[0]
            return ret
        finally:                    # Make sure to remove the tmp file
            file.close()
            os.remove(filename)

    def test_basic(self):
        """
        Try to create an empty pdf document
        """
        doc = PythonReader.read([])
        pdf = PDFWriter.write(doc).getvalue()
        html = self.pdf_to_html(pdf)

    def test_paragraph(self):
        """
        Try a simple document with one paragraph
        """
        doc = PythonReader.read(P[u"the text"])
        pdf = PDFWriter.write(doc).getvalue()
        html = self.pdf_to_html(pdf)
        assert "the text" in html

    def test_bold(self):
        doc = PythonReader.read([P[T(BOLD)[u"bold text"]]])
        pdf = PDFWriter.write(doc).getvalue()
        html = self.pdf_to_html(pdf)
        soup = BeautifulSoup.BeautifulSoup(html)
        node = soup.find("b")
        assert node
        assert node.string == "bold text"

    def test_italic(self):
        doc = PythonReader.read([P[T(ITALIC)[u"italic text"]]])
        pdf = PDFWriter.write(doc).getvalue()
        html = self.pdf_to_html(pdf)
        soup = BeautifulSoup.BeautifulSoup(html)
        node = soup.find("i")
        assert node
        assert node.string == "italic text"

    def test_latex(self):
        doc = PythonReader.read(P[u"the-text"])
        pdf = PDFWriter.write(doc).getvalue()
        html = self.pdf_to_html(pdf)
        assert "the-text" in html, html

    def test_rst(self):
        doc = PythonReader.read(P[u"the-text"])
        pdf = PDFWriter.write(doc).getvalue()
        print pdf
        html = self.pdf_to_html(pdf)
        assert "the-text" in html, html


if __name__ == '__main__':
    unittest.main()