DenysMedvid/pdf2htmlEX
1
0
Fork 0
mirror of https://github.com/pdf2htmlEX/pdf2htmlEX.git synced 2024-12-22 04:50:09 +00:00
Code

working on unittest

Browse Source 
use fontforge PPA in travis

exluding test/ in the archive

..

rewrite test_naming.py

migrate old test_nameing.py to new unittest
This commit is contained in:
Lu Wang 2014-11-14 20:29:36 +08:00
parent 2ca5ea6031
commit 22d19329c0
12 changed files with 164 additions and 244 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
.gitignore vendored
View File

@ -3,20 +3,18 @@ CMakeFiles/*
cmake_install.cmake
CTestTestfile.cmake
gmon.out
Makefile
install_manifest.txt
Makefile
pdf2htmlEX
pdf2htmlEX.1
*.pyc
share/base.css
share/base.min.css
share/fancy.css
share/js_src/css_class_names.js
share/fancy.min.css
share/pdf2htmlEX.js
share/pdf2htmlEX.min.js
src/pdf2htmlEX-config.h
src/util/css_const.h
test/*
test export-ignore
Testing/*
wiki/*
doc/*
/"\\"
/share/base.min.css
/share/fancy.min.css

10
.travis.yml
View File

@ -1,16 +1,10 @@
language: cpp
compiler: gcc
before_install:
- sudo add-apt-repository ppa:fontforge/fontforge --yes
- sudo add-apt-repository ppa:coolwanglu/pdf2htmlex --yes
- sudo apt-get update -qq
- sudo apt-get install -qq libpoppler-dev libspiro-dev libcairo-dev libfreetype6-dev libltdl-dev
install:
- export LIBRARY_PATH=/usr/local/lib
- export LD_LIBRARY_PATH=/usr/local/lib
- pushd ..
- wget 'https://github.com/coolwanglu/fontforge/archive/pdf2htmlEX.tar.gz' -O - | tar -zxf -
- pushd fontforge-pdf2htmlEX && ./autogen.sh && ./configure && make && sudo make install && popd
- popd
- sudo apt-get install -qq libpoppler-dev libspiro-dev libcairo-dev libfreetype6-dev libltdl-dev libfontforge-dev libpango1.0-dev
before_script:
- cmake -DENABLE_SVG=ON .
script:

3
CMakeLists.txt
View File

@ -203,5 +203,4 @@ install (FILES ${PDF2HTMLEX_RESOURCE} DESTINATION share/pdf2htmlEX)
install (FILES pdf2htmlEX.1 DESTINATION share/man/man1)
enable_testing()
add_test(test_naming
python ${CMAKE_SOURCE_DIR}/test/test_naming.py)
add_test(test python ${CMAKE_SOURCE_DIR}/test/test.py)

1
CTestCustom.cmake Normal file
View File

@ -0,0 +1 @@
SET(CTEST_CUSTOM_POST_TEST "cat Testing/Temporary/LastTest.log")

16
share/manifest
View File

@ -11,6 +11,7 @@
#
# Special
# If a line contains """ only, all text until next """ will be included
# #TEST_IGNORE_BEGIN & #TEST_IGNORE_END are used for unittest
#############
# Declaration - Do not modify
@ -28,8 +29,12 @@
# Styles
# base CSS styles - Do not modify
@base.min.css
# fancy CSS styles - Optional
#TEST_IGNORE_BEGIN
@fancy.min.css
#TEST_IGNORE_END
# PDF specific CSS styles - Do not modify
$css
@ -39,7 +44,9 @@ $css
# compatibility.min.js, extracted from PDF.js
# To support old browsers like IE9
#TEST_IGNORE_BEGIN
@compatibility.min.js
#TEST_IGNORE_END
# entry point of pdf2htmlEX.Viewer
# You can override default configuration by passing an object to the constructor of Viewer
@ -48,6 +55,7 @@ $css
# pdf2htmlEX.defaultViewer = new pdf2htmlEX.Viewer({
# 'key_handler' : false
# });
#TEST_IGNORE_BEGIN
@pdf2htmlEX.min.js
"""
<script>
@ -56,6 +64,8 @@ try{
}catch(e){}
</script>
"""
#TEST_IGNORE_END
#############
# Do not modify
@ -71,6 +81,8 @@ try{
# You can add a class 'opened' here if you want it always opened or you don't use pdf2htmlEX.js
# e.g.
# <div id="sidebar" class="opened">
#TEST_IGNORE_BEGIN
"""
<div id="sidebar">
"""
@ -83,6 +95,7 @@ $outline
</div>
</div>
"""
#TEST_IGNORE_END
#############
# The container of PDF pages
@ -100,6 +113,8 @@ $pages
# shown when loading a page via ajax
# The default appearance should be invisible
# The 'active' class will be added when it is used
#TEST_IGNORE_BEGIN
"""
<div class="loading-indicator">
"""
@ -107,6 +122,7 @@ $pages
"""
</div>
"""
#TEST_IGNORE_END
#############
# Do not modify

3
test/old/convert_to_woff.fontforge Normal file
View File

@ -0,0 +1,3 @@
Open($1);
Generate($1:r+".woff");
Quit(0);

24
test/old/test.py Executable file
View File

@ -0,0 +1,24 @@
#!/usr/bin/env python
DIR = 'pdf'
#DIR = '../../pdf.js/test/pdfs'
import os
import sys
with open('out.html','w') as outf:
outf.write('<!DOCTYPE html>\n<html><head><meta charset=\"utf-8\"></head><body><div style="position:absolute;top:0;left:0;width:80%;height:100%;"><iframe width="100%" height="100%" name="pdf"></iframe></div><div style="position:absolute;top:0;right:0;width:20%;height:100%;overflow:auto;text-align:right;">')
for f in os.listdir(DIR):
if not f.lower().endswith('.pdf'):
continue
print f
if os.system('pdf2htmlEX -l 10 --no-drm 1 --fit-width 1024 --dest-dir html --external-hint-tool="ttfautohint" "%s/%s"' % (DIR,f)) != 0:
print "error on ", f
sys.exit(-1)
ff = f[:-3]
outf.write('<a href="html/%shtml" target="pdf">%s</a><br/>' % (ff,ff))
outf.flush();
outf.write('</div></body></html>')

96
test/test.py
View File

@ -1,24 +1,88 @@
#!/usr/bin/env python
DIR = 'pdf'
#DIR = '../../pdf.js/test/pdfs'
import unittest
import os
import sys
import tempfile
import shutil
import subprocess
with open('out.html','w') as outf:
outf.write('<!DOCTYPE html>\n<html><head><meta charset=\"utf-8\"></head><body><div style="position:absolute;top:0;left:0;width:80%;height:100%;"><iframe width="100%" height="100%" name="pdf"></iframe></div><div style="position:absolute;top:0;right:0;width:20%;height:100%;overflow:auto;text-align:right;">')
class Common(object):
SRC_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
TEST_DIR = os.path.join(SRC_DIR, 'test')
DATA_DIR = os.path.join(SRC_DIR, 'share')
PDF2HTMLEX_PATH = os.path.join(SRC_DIR, 'pdf2htmlEX')
def setUp(self):
self.cur_temp_dir = tempfile.mkdtemp(prefix='pdf2htmlEX_test')
self.cur_data_dir = os.path.join(self.cur_temp_dir, 'share')
self.cur_output_dir = os.path.join(self.cur_temp_dir, 'out')
os.mkdir(self.cur_data_dir)
os.mkdir(self.cur_output_dir)
# filter manifest
with open(os.path.join(self.DATA_DIR, 'manifest')) as inf:
with open(os.path.join(self.cur_data_dir, 'manifest'), 'w') as outf:
ignore = False
for line in inf:
if ignore:
if line.startswith('#TEST_IGNORE_END'):
ignore = False
elif line.startswith('#TEST_IGNORE_BEGIN'):
ignore = True
else:
outf.write(line)
for f in os.listdir(DIR):
if not f.lower().endswith('.pdf'):
continue
print f
if os.system('pdf2htmlEX -l 10 --no-drm 1 --fit-width 1024 --dest-dir html --external-hint-tool="ttfautohint" "%s/%s"' % (DIR,f)) != 0:
print "error on ", f
sys.exit(-1)
# copy files
shutil.copy(os.path.join(self.DATA_DIR, 'base.min.css'),
os.path.join(self.cur_data_dir, 'base.min.css'))
ff = f[:-3]
outf.write('<a href="html/%shtml" target="pdf">%s</a><br/>' % (ff,ff))
outf.flush();
def tearDown(self):
shutil.rmtree(self.cur_temp_dir, True)
outf.write('</div></body></html>')
def run_pdf2htmlEX(self, args):
"""
Execute the pdf2htmlEX with the specified arguments.
:type args: list of values
:param args: list of arguments to pass to executable.
:return: an object of relevant info
"""
cmd = [self.PDF2HTMLEX_PATH,
'--data-dir', self.cur_data_dir,
'--dest-dir', self.cur_output_dir
]
for val in args:
cmd.append(str(val))
return_code = subprocess.call(cmd)
self.assertEquals(return_code, 0)
files = os.listdir(self.cur_output_dir)
files.sort()
return {
'return_code' : return_code,
'output_files' : files
}
if __name__ == '__main__':
if not os.path.isfile(Common.PDF2HTMLEX_PATH) or not os.access(Common.PDF2HTMLEX_PATH, os.X_OK):
print >> sys.stderr, "Cannot locate pdf2htmlEX executable. Make sure source was built before running this test."
exit(1)
suites = []
loader = unittest.TestLoader()
for module_name in ['test_naming']:
__import__(module_name)
suites.append(loader.loadTestsFromModule(sys.modules[module_name]))
failure_count = 0
runner = unittest.TextTestRunner(verbosity=2)
for suite in suites:
result = runner.run(suite)
failure_count += len(result.errors) + len(result.failures)
exit(failure_count)

241
test/test_naming.py
View File

@ -1,264 +1,85 @@
#!/usr/bin/env python
# Test --split-page and --page-filename
import unittest
import os
import sys
import tempfile
import shutil
import subprocess
# We assume that this file is put inside SRC_DIR/test
TEST_DIR = os.path.dirname(__file__)
# The location where our test PDFs are stored
TEST_DATA_DIR = os.path.join(TEST_DIR, 'test_data')
# The location where the base css file, etc is stored in the build folder
DATA_DIR = os.path.join(TEST_DIR, '../share')
from test import Common
# The script should be run in the directory containing the binary
# The location where the executable is generated by the build
PDF2HTMLEX_PATH = './pdf2htmlEX'
class OutputNamingTests(Common, unittest.TestCase):
def run_test_case(self, input_file, expected_output_files, args=[]):
args = list(args)
args.insert(0, os.path.join(self.TEST_DIR, 'test_naming', input_file))
self.assertEquals(self.run_pdf2htmlEX(args)['output_files'], sorted(expected_output_files))
def execute_pdf2htmlex_with_args(args):
"""
Execute the pdf2htmlEX with the specified arguments.
:type args: list of values
:param args: list of arguments to pass to executable. First part of each tuple is the argument, second part is the value.
:rtype: int
:return: The exit code of the command
"""
executable = os.path.abspath(PDF2HTMLEX_PATH)
cmd = [executable, '--data-dir', os.path.abspath(DATA_DIR)]
for val in args:
cmd.append(str(val))
return_code = subprocess.call(cmd)
if return_code != 0:
print >> sys.stderr, "Command return code %d: %s" % (return_code, ' '.join(cmd))
return return_code
def execute_pdf2htmlex_and_get_files(args):
"""
Execute the pdf2htmlEX with the specified arguments, and get the names of the output files. Will automatically create
a temporary directory for the output, pass that as the output dir to pdf2htmlEX, determine the files generated, and
clean up the temporary directory afterwards.
:type args: list of values
:param args: list of arguments to pass to executable. First part of each tuple is the argument, second part is the value.
:rtype: list of str
:return: List of the file names that were generated as output in alphabetical order. None if the command does not execute successfully.
"""
temp_dir = tempfile.mkdtemp()
try:
if execute_pdf2htmlex_with_args(['--dest-dir', temp_dir] + args) != 0:
return None
files = os.listdir(temp_dir)
files.sort()
return files
finally:
shutil.rmtree(path=temp_dir, ignore_errors=True)
def path_to_test_file(filename):
"""
Retrieve an absolute path to the specified test file.
:type filename:
:param filename: the name of the test file to get the path to
:rtype: str
:returns: the full path to the test file
"""
return os.path.abspath(os.path.join(TEST_DATA_DIR, filename))
class OutputNamingTests(unittest.TestCase):
def test_generate_single_html_default_name_single_page_pdf(self):
files = execute_pdf2htmlex_and_get_files([
path_to_test_file('1-page.pdf')
])
self.assertEquals(files, ['1-page.html'])
self.run_test_case('1-page.pdf', ['1-page.html'])
def test_generate_single_html_default_name_multiple_page_pdf(self):
files = execute_pdf2htmlex_and_get_files([
path_to_test_file('2-pages.pdf')
])
self.assertEquals(files, ['2-pages.html'])
self.run_test_case('2-pages.pdf', ['2-pages.html'])
def test_generate_single_html_specify_name_single_page_pdf(self):
files = execute_pdf2htmlex_and_get_files([
path_to_test_file('1-page.pdf'),
'foo.html'
])
self.assertEquals(files, ['foo.html'])
self.run_test_case('1-page.pdf', ['foo.html'], ['foo.html'])
def test_generate_single_html_specify_name_multiple_page_pdf(self):
files = execute_pdf2htmlex_and_get_files([
path_to_test_file('2-pages.pdf'),
'foo.html'
])
self.assertEquals(files, ['foo.html'])
self.run_test_case('2-pages.pdf', ['foo.html'], ['foo.html'])
def test_generate_split_pages_default_name_single_page(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
path_to_test_file('1-page.pdf')
])
self.assertEquals(files, sorted(['1-page.html', '1-page1.page']))
self.run_test_case('1-page.pdf', ['1-page.html', '1-page1.page'], ['--split-pages', 1])
def test_generate_split_pages_default_name_multiple_pages(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
path_to_test_file('3-pages.pdf')
])
self.assertEquals(files, sorted(['3-pages.html', '3-pages1.page', '3-pages2.page', '3-pages3.page']))
self.run_test_case('3-pages.pdf', ['3-pages.html', '3-pages1.page', '3-pages2.page', '3-pages3.page'], ['--split-pages', 1])
def test_generate_split_pages_specify_name_single_page(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'foo.xyz',
path_to_test_file('1-page.pdf'),
])
self.assertEquals(files, sorted(['1-page.html', 'foo1.xyz']))
self.run_test_case('1-page.pdf', ['1-page.html', 'foo1.xyz'], ['--split-pages', 1, '--page-filename', 'foo.xyz'])
def test_generate_split_pages_specify_name_multiple_pages(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'foo.xyz',
path_to_test_file('3-pages.pdf'),
])
self.assertEquals(files, sorted(['3-pages.html', 'foo1.xyz', 'foo2.xyz', 'foo3.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'foo1.xyz', 'foo2.xyz', 'foo3.xyz'], ['--split-pages', 1, '--page-filename', 'foo.xyz'])
def test_generate_split_pages_specify_name_formatter_multiple_pages(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'fo%do.xyz',
path_to_test_file('3-pages.pdf'),
])
self.assertEquals(files, sorted(['3-pages.html', 'fo1o.xyz', 'fo2o.xyz', 'fo3o.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'fo1o.xyz', 'fo2o.xyz', 'fo3o.xyz'], ['--split-pages', 1, '--page-filename', 'fo%do.xyz'])
def test_generate_split_pages_specify_name_formatter_with_padded_zeros_multiple_pages(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'fo%03do.xyz',
path_to_test_file('3-pages.pdf')
])
self.assertEquals(files, sorted(['3-pages.html', 'fo001o.xyz', 'fo002o.xyz', 'fo003o.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'fo001o.xyz', 'fo002o.xyz', 'fo003o.xyz'], ['--split-pages', 1, '--page-filename', 'fo%03do.xyz'])
def test_generate_split_pages_specify_name_only_first_formatter_gets_taken(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'f%do%do.xyz',
path_to_test_file('3-pages.pdf')
])
self.assertEquals(files, sorted(['3-pages.html', 'f1o%do.xyz', 'f2o%do.xyz', 'f3o%do.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'f1o%do.xyz', 'f2o%do.xyz', 'f3o%do.xyz'], ['--split-pages', 1, '--page-filename', 'f%do%do.xyz'])
def test_generate_split_pages_specify_name_only_percent_d_is_used_percent_s(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'f%soo.xyz',
path_to_test_file('3-pages.pdf')
])
self.assertEquals(files, sorted(['3-pages.html', 'f%soo1.xyz', 'f%soo2.xyz', 'f%soo3.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'f%soo1.xyz', 'f%soo2.xyz', 'f%soo3.xyz'], ['--split-pages', 1, '--page-filename', 'f%soo.xyz'])
def test_generate_split_pages_specify_name_only_percent_d_is_used_percent_p(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'f%poo.xyz',
path_to_test_file('3-pages.pdf'),
])
self.assertEquals(files, sorted(['3-pages.html', 'f%poo1.xyz', 'f%poo2.xyz', 'f%poo3.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'f%poo1.xyz', 'f%poo2.xyz', 'f%poo3.xyz'], ['--split-pages', 1, '--page-filename', 'f%poo.xyz'])
def test_generate_split_pages_specify_name_only_percent_d_is_used_percent_n(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'f%noo.xyz',
path_to_test_file('3-pages.pdf')
])
self.assertEquals(files, sorted(['3-pages.html', 'f%noo1.xyz', 'f%noo2.xyz', 'f%noo3.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'f%noo1.xyz', 'f%noo2.xyz', 'f%noo3.xyz'], ['--split-pages', 1, '--page-filename', 'f%noo.xyz'])
def test_generate_split_pages_specify_name_only_percent_d_is_used_percent_percent(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'f%%oo.xyz',
path_to_test_file('3-pages.pdf')
])
self.assertEquals(files, sorted(['3-pages.html', 'f%%oo1.xyz', 'f%%oo2.xyz', 'f%%oo3.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'f%%oo1.xyz', 'f%%oo2.xyz', 'f%%oo3.xyz'], ['--split-pages', 1, '--page-filename', 'f%%oo.xyz'])
def test_generate_split_pages_specify_name_only_percent_d_is_used_percent_percent_with_actual_placeholder(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'f%%o%do.xyz',
path_to_test_file('3-pages.pdf')
])
self.assertEquals(files, sorted(['3-pages.html', 'f%%o1o.xyz', 'f%%o2o.xyz', 'f%%o3o.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'f%%o1o.xyz', 'f%%o2o.xyz', 'f%%o3o.xyz'], ['--split-pages', 1, '--page-filename', 'f%%o%do.xyz'])
def test_generate_split_pages_specify_name_only_percent_d_is_used_percent_percent_with_actual_placeholder(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'fo%do%%.xyz',
path_to_test_file('3-pages.pdf')
])
self.assertEquals(files, sorted(['3-pages.html', 'fo1o%%.xyz', 'fo2o%%.xyz', 'fo3o%%.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'fo1o%%.xyz', 'fo2o%%.xyz', 'fo3o%%.xyz'], ['--split-pages', 1, '--page-filename', 'fo%do%%.xyz'])
def test_generate_split_pages_specify_name_only_formatter_starts_part_way_through_invalid_formatter(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'f%02%doo.xyz',
path_to_test_file('3-pages.pdf'),
])
self.assertEquals(files, sorted(['3-pages.html', 'f%021oo.xyz', 'f%022oo.xyz', 'f%023oo.xyz']))
self.run_test_case('3-pages.pdf', ['3-pages.html', 'f%021oo.xyz', 'f%022oo.xyz', 'f%023oo.xyz'], ['--split-pages', 1, '--page-filename', 'f%02%doo.xyz'])
def test_generate_split_pages_specify_output_filename_no_formatter_no_extension(self):
files = execute_pdf2htmlex_and_get_files([
'--split-pages', 1,
'--page-filename', 'foo',
path_to_test_file('1-page.pdf'),
])
self.assertEquals(files, sorted(['1-page.html', 'foo1']))
self.run_test_case('1-page.pdf', ['1-page.html', 'foo1'], ['--split-pages', 1, '--page-filename', 'foo'])
def test_generate_single_html_name_specified_format_characters_percent_d(self):
files = execute_pdf2htmlex_and_get_files([
path_to_test_file('2-pages.pdf'),
'foo%d.html'
])
self.assertEquals(files, ['foo%d.html'])
self.run_test_case('2-pages.pdf', ['foo%d.html'], ['foo%d.html'])
def test_generate_single_html_name_specified_format_characters_percent_p(self):
files = execute_pdf2htmlex_and_get_files([
path_to_test_file('2-pages.pdf'),
'foo%p.html'
])
self.assertEquals(files, ['foo%p.html'])
self.run_test_case('2-pages.pdf', ['foo%p.html'], ['foo%p.html'])
def test_generate_single_html_name_specified_format_characters_percent_n(self):
files = execute_pdf2htmlex_and_get_files([
path_to_test_file('2-pages.pdf'),
'foo%n.html'
])
self.assertEquals(files, ['foo%n.html'])
self.run_test_case('2-pages.pdf', ['foo%n.html'], ['foo%n.html'])
def test_generate_single_html_name_specified_format_characters_percent_percent(self):
files = execute_pdf2htmlex_and_get_files([
path_to_test_file('2-pages.pdf'),
'foo%%.html'
])
self.assertEquals(files, ['foo%%.html'])
self.run_test_case('2-pages.pdf', ['foo%%.html'], ['foo%%.html'])
if __name__=="__main__":
executable = os.path.abspath(PDF2HTMLEX_PATH)
if not os.path.isfile(executable) or not os.access(executable, os.X_OK):
print >> sys.stderr, "Cannot locate pdf2htmlEX executable. Make sure source was built before running this test."
exit(1)
# we want to run pdf2htmlEX without installing it
shutil.copy(os.path.join(TEST_DIR, '../3rdparty/PDF.js/compatibility.min.js'), DATA_DIR)
unittest.main()

0
test/test_data/1-page.pdf → test/test_naming/1-page.pdf
View File

0
test/test_data/2-pages.pdf → test/test_naming/2-pages.pdf
View File

0
test/test_data/3-pages.pdf → test/test_naming/3-pages.pdf
View File