def test_metadata():
model_metadata = {
'English': 'eggs',
u('Русский'): u('яйца'),
}
meta = '\n'.join(
u('|{k}| {v}').format(k=k, v=v) for k, v in model_metadata.items())
test_script = u('set-meta\n{meta}\n.\n').format(meta=meta)
try:
test_file = create_djvu(test_script)
except UnicodeEncodeError:
raise SkipTest(
'you need to run this test with LC_CTYPE=C or LC_CTYPE=<lang>.UTF-8'
)
try:
context = Context()
document = context.new_document(FileUri(test_file.name))
message = document.get_message()
assert_equal(type(message), DocInfoMessage)
annotations = document.annotations
assert_equal(type(annotations), DocumentAnnotations)
annotations.wait()
metadata = annotations.metadata
assert_equal(type(metadata), Metadata)
assert_equal(len(metadata), len(model_metadata))
assert_equal(sorted(metadata), sorted(model_metadata))
if not py3k:
assert_equal(sorted(metadata.iterkeys()),
sorted(model_metadata.iterkeys()))
assert_equal(sorted(metadata.keys()), sorted(model_metadata.keys()))
if not py3k:
assert_equal(sorted(metadata.itervalues()),
sorted(model_metadata.itervalues()))
assert_equal(sorted(metadata.values()),
sorted(model_metadata.values()))
if not py3k:
assert_equal(sorted(metadata.iteritems()),
sorted(model_metadata.iteritems()))
assert_equal(sorted(metadata.items()), sorted(model_metadata.items()))
for k in metadata:
assert_equal(type(k), unicode)
assert_equal(type(metadata[k]), unicode)
for k in None, 42, '+'.join(model_metadata):
with assert_raises(KeyError) as ecm:
metadata[k]
assert_equal(ecm.exception.args, (k, ))
finally:
test_file.close()
def test_nonexistent_ja(self):
skip_unless_c_messages()
skip_unless_translation_exists('ja_JP.UTF-8')
path = '__nonexistent__'
context = Context()
try:
with interim_locale(LC_ALL='ja_JP.UTF-8'):
os.stat(path)
except OSError as ex:
c_message = ex.args[1]
else:
raise OSError(errno.EEXIST, os.strerror(errno.EEXIST), path)
try:
c_message.encode('ASCII')
except UnicodeError:
pass
else:
raise AssertionError(
'ja_JP error message is ASCII-only: {msg!r}'.format(
msg=c_message))
with interim_locale(LC_ALL='ja_JP.UTF-8'):
with assert_raises(JobFailed):
context.new_document(FileUri(path))
message = context.get_message()
assert_equal(type(message), ErrorMessage)
assert_equal(type(message.message), unicode)
assert_equal(
message.message,
u("[1-11711] Failed to open '{path}': {msg}.".format(
path=path, msg=c_message)))
assert_equal(
str(message),
"[1-11711] Failed to open '{path}': {msg}.".format(
path=path, msg=c_message))
assert_equal(unicode(message), message.message)
def test_nonexistent_ja(self):
skip_unless_c_messages()
skip_unless_translation_exists('ja_JP.UTF-8')
path = '__nonexistent__'
context = Context()
try:
with interim_locale(LC_ALL='ja_JP.UTF-8'):
os.stat(path)
except OSError as ex:
c_message = ex.args[1]
else:
raise OSError(errno.EEXIST, os.strerror(errno.EEXIST), path)
try:
c_message.encode('ASCII')
except UnicodeError:
pass
else:
raise AssertionError(
'ja_JP error message is ASCII-only: {msg!r}'.format(msg=c_message)
)
with interim_locale(LC_ALL='ja_JP.UTF-8'):
with assert_raises(JobFailed):
context.new_document(FileUri(path))
message = context.get_message()
assert_equal(type(message), ErrorMessage)
assert_equal(type(message.message), unicode)
assert_equal(
message.message,
u("[1-11711] Failed to open '{path}': {msg}.".format(path=path, msg=c_message))
)
assert_equal(
str(message),
"[1-11711] Failed to open '{path}': {msg}.".format(path=path, msg=c_message)
)
assert_equal(unicode(message), message.message)
def test_codecs_io_text_8(self):
tmpdir = tempfile.mkdtemp()
try:
path = os.path.join(tmpdir, 'tmp')
with codecs.open(path, mode='w+', encoding='UTF-16-LE') as fp:
self.expr.print_into(fp, escape_unicode=False)
fp.seek(0)
assert_equal(fp.read(), u(self.urepr))
finally:
shutil.rmtree(tmpdir)
def test_codecs_io_text_8(self):
tmpdir = tempfile.mkdtemp()
try:
path = os.path.join(tmpdir, 'tmp')
with codecs.open(path, mode='w+', encoding='UTF-16-LE') as fp:
self.expr.print_into(fp, escape_unicode=False)
fp.seek(0)
assert_equal(fp.read(), u(self.urepr))
finally:
shutil.rmtree(tmpdir)
def test_codecs_io(self):
tmpdir = tempfile.mkdtemp()
try:
path = os.path.join(tmpdir, 'tmp')
with codecs.open(path, mode='w+', encoding='UTF-16-LE') as fp:
fp.write(u(self.expr))
fp.seek(0)
self.t(fp)
finally:
shutil.rmtree(tmpdir)
def test_codecs_io(self):
tmpdir = tempfile.mkdtemp()
try:
path = os.path.join(tmpdir, 'tmp')
with codecs.open(path, mode='w+', encoding='UTF-16-LE') as fp:
fp.write(u(self.expr))
fp.seek(0)
self.t(fp)
finally:
shutil.rmtree(tmpdir)
def test_metadata():
model_metadata = {
'English': 'eggs',
u('Русский'): u('яйца'),
}
meta = '\n'.join(u('|{k}| {v}').format(k=k, v=v) for k, v in model_metadata.items())
test_script = u('set-meta\n{meta}\n.\n').format(meta=meta)
try:
test_file = create_djvu(test_script)
except UnicodeEncodeError:
raise SkipTest('you need to run this test with LC_CTYPE=C or LC_CTYPE=<lang>.UTF-8')
try:
context = Context()
document = context.new_document(FileUri(test_file.name))
message = document.get_message()
assert_equal(type(message), DocInfoMessage)
annotations = document.annotations
assert_equal(type(annotations), DocumentAnnotations)
annotations.wait()
metadata = annotations.metadata
assert_equal(type(metadata), Metadata)
assert_equal(len(metadata), len(model_metadata))
assert_equal(sorted(metadata), sorted(model_metadata))
if not py3k:
assert_equal(sorted(metadata.iterkeys()), sorted(model_metadata.iterkeys()))
assert_equal(sorted(metadata.keys()), sorted(model_metadata.keys()))
if not py3k:
assert_equal(sorted(metadata.itervalues()), sorted(model_metadata.itervalues()))
assert_equal(sorted(metadata.values()), sorted(model_metadata.values()))
if not py3k:
assert_equal(sorted(metadata.iteritems()), sorted(model_metadata.iteritems()))
assert_equal(sorted(metadata.items()), sorted(model_metadata.items()))
for k in metadata:
assert_equal(type(k), unicode)
assert_equal(type(metadata[k]), unicode)
for k in None, 42, '+'.join(model_metadata):
with assert_raises(KeyError) as ecm:
metadata[k]
assert_equal(ecm.exception.args, (k,))
finally:
test_file.close()
def test2(self):
x = Expression(u('żółw'))
if py3k:
assert_repr(x, "Expression('żółw')")
else:
assert_repr(x, r"Expression('\xc5\xbc\xc3\xb3\xc5\x82w')")
def test1(self):
x = Expression(u('eggs'))
assert_repr(x, "Expression('eggs')")
assert_is(x, Expression(x))
def test_nonascii(self):
x = self.t(b('ветчина'), '|ветчина|')
y = self.t(u('ветчина'), '|ветчина|')
assert_equal(x, y)
assert_equal(hash(x), hash(y))
def test_nonascii(self):
x = self.t(b('ветчина'), 'ветчина')
y = self.t(u('ветчина'), 'ветчина')
assert x is y
class test_expression_writer_nonascii(test_expression_writer_ascii):
expr = Expression(u('żółw'))
repr = r'"\305\274\303\263\305\202w"'
urepr = r'"żółw"'
def test_new_document(self):
context = Context()
document = context.new_document(FileUri(images + 'test1.djvu'))
assert_equal(type(document), Document)
message = document.get_message()
assert_equal(type(message), DocInfoMessage)
assert_true(document.decoding_done)
assert_false(document.decoding_error)
assert_equal(document.decoding_status, JobOK)
assert_equal(document.type, DOCUMENT_TYPE_SINGLE_PAGE)
assert_equal(len(document.pages), 1)
assert_equal(len(document.files), 1)
decoding_job = document.decoding_job
assert_true(decoding_job.is_done)
assert_false(decoding_job.is_error)
assert_equal(decoding_job.status, JobOK)
file = document.files[0]
assert_is(type(file), File)
assert_is(file.document, document)
assert_is(file.get_info(), None)
assert_equal(file.type, 'P')
assert_equal(file.n_page, 0)
page = file.page
assert_equal(type(page), Page)
assert_is(page.document, document)
assert_equal(page.n, 0)
assert_is(file.size, None)
assert_equal(file.id, u('test1.djvu'))
assert_equal(type(file.id), unicode)
assert_equal(file.name, u('test1.djvu'))
assert_equal(type(file.name), unicode)
assert_equal(file.title, u('test1.djvu'))
assert_equal(type(file.title), unicode)
dump = document.files[0].dump
assert_equal(type(dump), unicode)
assert_equal([line for line in dump.splitlines()], [
u(' FORM:DJVU [83] '),
u(' INFO [10] DjVu 64x48, v24, 300 dpi, gamma=2.2'),
u(' Sjbz [53] JB2 bilevel data'),
])
page = document.pages[0]
assert_equal(type(page), Page)
assert_is(page.document, document)
assert_is(page.get_info(), None)
assert_equal(page.width, 64)
assert_equal(page.height, 48)
assert_equal(page.size, (64, 48))
assert_equal(page.dpi, 300)
assert_equal(page.rotation, 0)
assert_equal(page.version, 24)
file = page.file
assert_equal(type(file), File)
assert_equal(file.id, u('test1.djvu'))
assert_equal(type(file.id), unicode)
dump = document.files[0].dump
assert_equal(type(dump), unicode)
assert_equal([line for line in dump.splitlines()], [
u(' FORM:DJVU [83] '),
u(' INFO [10] DjVu 64x48, v24, 300 dpi, gamma=2.2'),
u(' Sjbz [53] JB2 bilevel data'),
])
assert_is(document.get_message(wait=False), None)
assert_is(context.get_message(wait=False), None)
with assert_raises_str(IndexError, 'file number out of range'):
document.files[-1].get_info()
assert_is(document.get_message(wait=False), None)
assert_is(context.get_message(wait=False), None)
with assert_raises_str(IndexError, 'page number out of range'):
document.pages[-1]
with assert_raises_str(IndexError, 'page number out of range'):
document.pages[1]
assert_is(document.get_message(wait=False), None)
assert_is(context.get_message(wait=False), None)
def test2(self):
x = Expression(u('żółw'))
if py3k:
assert_repr(x, "Expression('żółw')")
else:
assert_repr(x, r"Expression('\xc5\xbc\xc3\xb3\xc5\x82w')")
def test_new_document(self):
context = Context()
document = context.new_document(FileUri(images + 'test1.djvu'))
assert_equal(type(document), Document)
message = document.get_message()
assert_equal(type(message), DocInfoMessage)
assert_true(document.decoding_done)
assert_false(document.decoding_error)
assert_equal(document.decoding_status, JobOK)
assert_equal(document.type, DOCUMENT_TYPE_SINGLE_PAGE)
assert_equal(len(document.pages), 1)
assert_equal(len(document.files), 1)
decoding_job = document.decoding_job
assert_true(decoding_job.is_done)
assert_false(decoding_job.is_error)
assert_equal(decoding_job.status, JobOK)
file = document.files[0]
assert_is(type(file), File)
assert_is(file.document, document)
assert_is(file.get_info(), None)
assert_equal(file.type, 'P')
assert_equal(file.n_page, 0)
page = file.page
assert_equal(type(page), Page)
assert_is(page.document, document)
assert_equal(page.n, 0)
assert_is(file.size, None)
assert_equal(file.id, u('test1.djvu'))
assert_equal(type(file.id), unicode)
assert_equal(file.name, u('test1.djvu'))
assert_equal(type(file.name), unicode)
assert_equal(file.title, u('test1.djvu'))
assert_equal(type(file.title), unicode)
dump = document.files[0].dump
assert_equal(type(dump), unicode)
assert_equal(
[line for line in dump.splitlines()], [
u(' FORM:DJVU [83] '),
u(' INFO [10] DjVu 64x48, v24, 300 dpi, gamma=2.2'),
u(' Sjbz [53] JB2 bilevel data'),
]
)
page = document.pages[0]
assert_equal(type(page), Page)
assert_is(page.document, document)
assert_is(page.get_info(), None)
assert_equal(page.width, 64)
assert_equal(page.height, 48)
assert_equal(page.size, (64, 48))
assert_equal(page.dpi, 300)
assert_equal(page.rotation, 0)
assert_equal(page.version, 24)
file = page.file
assert_equal(type(file), File)
assert_equal(file.id, u('test1.djvu'))
assert_equal(type(file.id), unicode)
dump = document.files[0].dump
assert_equal(type(dump), unicode)
assert_equal(
[line for line in dump.splitlines()], [
u(' FORM:DJVU [83] '),
u(' INFO [10] DjVu 64x48, v24, 300 dpi, gamma=2.2'),
u(' Sjbz [53] JB2 bilevel data'),
]
)
assert_is(document.get_message(wait=False), None)
assert_is(context.get_message(wait=False), None)
with assert_raises_str(IndexError, 'file number out of range'):
document.files[-1].get_info()
assert_is(document.get_message(wait=False), None)
assert_is(context.get_message(wait=False), None)
with assert_raises_str(IndexError, 'page number out of range'):
document.pages[-1]
with assert_raises_str(IndexError, 'page number out of range'):
document.pages[1]
assert_is(document.get_message(wait=False), None)
assert_is(context.get_message(wait=False), None)
def test_nonascii(self):
x = self.t(b('ветчина'), '|ветчина|')
y = self.t(u('ветчина'), '|ветчина|')
assert_equal(x, y)
assert_equal(hash(x), hash(y))
def test_nonascii(self):
x = self.t(b('ветчина'), 'ветчина')
y = self.t(u('ветчина'), 'ветчина')
assert x is y
def test(self):
context = Context()
document = context.new_document(FileUri(images + 'test0.djvu'))
assert_equal(type(document), Document)
message = document.get_message()
assert_equal(type(message), DocInfoMessage)
anno = DocumentAnnotations(document, shared=False)
assert_equal(type(anno), DocumentAnnotations)
anno.wait()
x = anno.sexpr
assert_equal(x, Expression([]))
anno = document.annotations
assert_equal(type(anno), DocumentAnnotations)
anno.wait()
assert_is(anno.background_color, None)
assert_is(anno.horizontal_align, None)
assert_is(anno.vertical_align, None)
assert_is(anno.mode, None)
assert_is(anno.zoom, None)
expected_metadata = [
Symbol('metadata'),
[Symbol('ModDate'), '2015-08-17 19:54:57+02:00'],
[Symbol('CreationDate'), '2015-08-17 19:54:57+02:00'],
[Symbol('Producer'), 'pdfTeX-1.40.16'],
[Symbol('Creator'), 'LaTeX with hyperref package'],
[Symbol('Author'), 'Jakub Wilk']
]
expected_xmp = [
Symbol('xmp'),
'<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">'
'<rdf:Description rdf:about="">'
'<xmpMM:History xmlns:xmpMM="http://ns.adobe.com/xap/1.0/mm/"><rdf:Seq><rdf:li xmlns:stEvt="http://ns.adobe.com/xap/1.0/sType/ResourceEvent#" stEvt:action="converted" stEvt:parameters="from application/pdf to image/vnd.djvu" stEvt:softwareAgent="pdf2djvu 0.8.1 (DjVuLibre 3.5.27, Poppler 0.26.5, GraphicsMagick++ 1.3.21, GNOME XSLT 1.1.28, GNOME XML 2.9.2, PStreams 0.8.0)" stEvt:when="2015-08-17T17:54:58+00:00"/></rdf:Seq></xmpMM:History>'
'<dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Jakub Wilk</dc:creator>'
'<dc:format xmlns:dc="http://purl.org/dc/elements/1.1/">image/vnd.djvu</dc:format>'
'<pdf:Producer xmlns:pdf="http://ns.adobe.com/pdf/1.3/">pdfTeX-1.40.16</pdf:Producer>'
'<xmp:CreatorTool xmlns:xmp="http://ns.adobe.com/xap/1.0/">LaTeX with hyperref package</xmp:CreatorTool>'
'<xmp:CreateDate xmlns:xmp="http://ns.adobe.com/xap/1.0/">2015-08-17T19:54:57+02:00</xmp:CreateDate>'
'<xmp:ModifyDate xmlns:xmp="http://ns.adobe.com/xap/1.0/">2015-08-17T19:54:57+02:00</xmp:ModifyDate>'
'<xmp:MetadataDate xmlns:xmp="http://ns.adobe.com/xap/1.0/">2015-08-17T17:54:58+00:00</xmp:MetadataDate>'
'</rdf:Description>'
'</rdf:RDF>\n'
]
assert_equal(anno.sexpr, Expression([expected_metadata, expected_xmp]))
metadata = anno.metadata
assert_equal(type(metadata), Metadata)
hyperlinks = anno.hyperlinks
assert_equal(type(hyperlinks), Hyperlinks)
assert_equal(len(hyperlinks), 0)
assert_equal(list(hyperlinks), [])
outline = document.outline
assert_equal(type(outline), DocumentOutline)
outline.wait()
assert_equal(
outline.sexpr,
Expression([
Symbol('bookmarks'), ['Lorem ipsum', '#p0001.djvu'],
[
'Hyperlinks', '#p0002.djvu', ['local', '#p0002.djvu'],
['remote', '#p0002.djvu']
]
]))
page = document.pages[1]
anno = page.annotations
assert_equal(type(anno), PageAnnotations)
anno.wait()
assert_is(anno.background_color, None)
assert_is(anno.horizontal_align, None)
assert_is(anno.vertical_align, None)
assert_is(anno.mode, None)
assert_is(anno.zoom, None)
expected_hyperlinks = [[
Symbol('maparea'), '#p0001.djvu', '',
[Symbol('rect'), 520, 2502, 33, 42],
[Symbol('border'), Symbol('#ff0000')]
],
[
Symbol('maparea'), 'http://jwilk.net/', '',
[Symbol('rect'), 458, 2253, 516, 49],
[Symbol('border'),
Symbol('#00ffff')]
]]
assert_equal(
anno.sexpr,
Expression([expected_metadata, expected_xmp] +
expected_hyperlinks))
page_metadata = anno.metadata
assert_equal(type(page_metadata), Metadata)
assert_equal(page_metadata.keys(), metadata.keys())
assert_equal([page_metadata[k] == metadata[k] for k in metadata],
[True, True, True, True, True])
hyperlinks = anno.hyperlinks
assert_equal(type(hyperlinks), Hyperlinks)
assert_equal(len(hyperlinks), 2)
assert_equal(list(hyperlinks),
[Expression(h) for h in expected_hyperlinks])
text = page.text
assert_equal(type(text), PageText)
text.wait()
text_s = text.sexpr
text_s_detail = [
PageText(page, details).sexpr
for details in (TEXT_DETAILS_PAGE, TEXT_DETAILS_COLUMN,
TEXT_DETAILS_REGION, TEXT_DETAILS_PARAGRAPH,
TEXT_DETAILS_LINE, TEXT_DETAILS_WORD,
TEXT_DETAILS_CHARACTER, TEXT_DETAILS_ALL)
]
assert_equal(text_s_detail[0], text_s_detail[1])
assert_equal(text_s_detail[1], text_s_detail[2])
assert_equal(text_s_detail[2], text_s_detail[3])
assert_equal(
text_s_detail[0],
Expression([
Symbol('page'), 0, 0, 2550, 3300, '2 Hyperlinks \n'
'2.1 local \n' + u('→1 \n') +
'2.2 remote \nhttp://jwilk.net/ \n'
'2 \n'
]))
assert_equal(
text_s_detail[4],
Expression([
Symbol('page'), 0, 0, 2550, 3300,
[Symbol('line'), 462, 2712, 910, 2777, '2 Hyperlinks '],
[Symbol('line'), 462, 2599, 714, 2641, '2.1 local '],
[Symbol('line'), 464, 2505, 544, 2540,
u('→1 ')],
[Symbol('line'), 462, 2358, 772, 2400, '2.2 remote '],
[Symbol('line'), 463, 2256, 964, 2298, 'http://jwilk.net/ '],
[Symbol('line'), 1260, 375, 1282, 409, '2 ']
]))
assert_equal(text_s_detail[5], text_s)
assert_equal(text_s_detail[6], text_s)
assert_equal(text_s_detail[7], text_s)
assert_equal(
text_s,
Expression([
Symbol('page'), 0, 0, 2550, 3300,
[
Symbol('line'), 462, 2712, 910, 2777,
[Symbol('word'), 462, 2727, 495, 2776, '2'],
[Symbol('word'), 571, 2712, 910, 2777, 'Hyperlinks']
],
[
Symbol('line'), 462, 2599, 714, 2641,
[Symbol('word'), 462, 2599, 532, 2641, '2.1'],
[Symbol('word'), 597, 2599, 714, 2640, 'local']
],
[
Symbol('line'), 464, 2505, 544, 2540,
[Symbol('word'), 464, 2505, 544, 2540,
u('→1')]
],
[
Symbol('line'), 462, 2358, 772, 2400,
[Symbol('word'), 462, 2358, 535, 2400, '2.2'],
[Symbol('word'), 598, 2358, 772, 2397, 'remote']
],
[
Symbol('line'), 463, 2256, 964, 2298,
[
Symbol('word'), 463, 2256, 964, 2298,
'http://jwilk.net/'
]
],
[
Symbol('line'), 1260, 375, 1282, 409,
[Symbol('word'), 1260, 375, 1282, 409, '2']
]
]))
with assert_raises_str(TypeError, 'details must be a symbol or none'):
PageText(page, 'eggs')
with assert_raises_str(
ValueError,
'details must be equal to TEXT_DETAILS_PAGE, or TEXT_DETAILS_COLUMN, or TEXT_DETAILS_REGION, or TEXT_DETAILS_PARAGRAPH, or TEXT_DETAILS_LINE, or TEXT_DETAILS_WORD, or TEXT_DETAILS_CHARACTER or TEXT_DETAILS_ALL'
):
PageText(page, Symbol('eggs'))
def test1(self):
x = Expression(u('eggs'))
assert_repr(x, "Expression('eggs')")
assert_is(x, Expression(x))
def test(self):
context = Context()
document = context.new_document(FileUri(images + 'test0.djvu'))
assert_equal(type(document), Document)
message = document.get_message()
assert_equal(type(message), DocInfoMessage)
anno = DocumentAnnotations(document, shared=False)
assert_equal(type(anno), DocumentAnnotations)
anno.wait()
x = anno.sexpr
assert_equal(x, Expression([]))
anno = document.annotations
assert_equal(type(anno), DocumentAnnotations)
anno.wait()
assert_is(anno.background_color, None)
assert_is(anno.horizontal_align, None)
assert_is(anno.vertical_align, None)
assert_is(anno.mode, None)
assert_is(anno.zoom, None)
expected_metadata = [
Symbol('metadata'),
[Symbol('ModDate'), '2015-08-17 19:54:57+02:00'],
[Symbol('CreationDate'), '2015-08-17 19:54:57+02:00'],
[Symbol('Producer'), 'pdfTeX-1.40.16'],
[Symbol('Creator'), 'LaTeX with hyperref package'],
[Symbol('Author'), 'Jakub Wilk']
]
expected_xmp = [
Symbol('xmp'),
'<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">'
'<rdf:Description rdf:about="">'
'<xmpMM:History xmlns:xmpMM="http://ns.adobe.com/xap/1.0/mm/"><rdf:Seq><rdf:li xmlns:stEvt="http://ns.adobe.com/xap/1.0/sType/ResourceEvent#" stEvt:action="converted" stEvt:parameters="from application/pdf to image/vnd.djvu" stEvt:softwareAgent="pdf2djvu 0.8.1 (DjVuLibre 3.5.27, Poppler 0.26.5, GraphicsMagick++ 1.3.21, GNOME XSLT 1.1.28, GNOME XML 2.9.2, PStreams 0.8.0)" stEvt:when="2015-08-17T17:54:58+00:00"/></rdf:Seq></xmpMM:History>'
'<dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Jakub Wilk</dc:creator>'
'<dc:format xmlns:dc="http://purl.org/dc/elements/1.1/">image/vnd.djvu</dc:format>'
'<pdf:Producer xmlns:pdf="http://ns.adobe.com/pdf/1.3/">pdfTeX-1.40.16</pdf:Producer>'
'<xmp:CreatorTool xmlns:xmp="http://ns.adobe.com/xap/1.0/">LaTeX with hyperref package</xmp:CreatorTool>'
'<xmp:CreateDate xmlns:xmp="http://ns.adobe.com/xap/1.0/">2015-08-17T19:54:57+02:00</xmp:CreateDate>'
'<xmp:ModifyDate xmlns:xmp="http://ns.adobe.com/xap/1.0/">2015-08-17T19:54:57+02:00</xmp:ModifyDate>'
'<xmp:MetadataDate xmlns:xmp="http://ns.adobe.com/xap/1.0/">2015-08-17T17:54:58+00:00</xmp:MetadataDate>'
'</rdf:Description>'
'</rdf:RDF>\n'
]
assert_equal(
anno.sexpr,
Expression([expected_metadata, expected_xmp])
)
metadata = anno.metadata
assert_equal(type(metadata), Metadata)
hyperlinks = anno.hyperlinks
assert_equal(type(hyperlinks), Hyperlinks)
assert_equal(len(hyperlinks), 0)
assert_equal(list(hyperlinks), [])
outline = document.outline
assert_equal(type(outline), DocumentOutline)
outline.wait()
assert_equal(outline.sexpr, Expression(
[Symbol('bookmarks'),
['Lorem ipsum', '#p0001.djvu'],
['Hyperlinks', '#p0002.djvu',
['local', '#p0002.djvu'],
['remote', '#p0002.djvu']
]
]
))
page = document.pages[1]
anno = page.annotations
assert_equal(type(anno), PageAnnotations)
anno.wait()
assert_is(anno.background_color, None)
assert_is(anno.horizontal_align, None)
assert_is(anno.vertical_align, None)
assert_is(anno.mode, None)
assert_is(anno.zoom, None)
expected_hyperlinks = [
[Symbol('maparea'), '#p0001.djvu', '', [Symbol('rect'), 520, 2502, 33, 42], [Symbol('border'), Symbol('#ff0000')]],
[Symbol('maparea'), 'http://jwilk.net/', '', [Symbol('rect'), 458, 2253, 516, 49], [Symbol('border'), Symbol('#00ffff')]]
]
assert_equal(
anno.sexpr,
Expression([expected_metadata, expected_xmp] + expected_hyperlinks)
)
page_metadata = anno.metadata
assert_equal(type(page_metadata), Metadata)
assert_equal(page_metadata.keys(), metadata.keys())
assert_equal([page_metadata[k] == metadata[k] for k in metadata], [True, True, True, True, True])
hyperlinks = anno.hyperlinks
assert_equal(type(hyperlinks), Hyperlinks)
assert_equal(len(hyperlinks), 2)
assert_equal(
list(hyperlinks),
[Expression(h) for h in expected_hyperlinks]
)
text = page.text
assert_equal(type(text), PageText)
text.wait()
text_s = text.sexpr
text_s_detail = [PageText(page, details).sexpr for details in (TEXT_DETAILS_PAGE, TEXT_DETAILS_COLUMN, TEXT_DETAILS_REGION, TEXT_DETAILS_PARAGRAPH, TEXT_DETAILS_LINE, TEXT_DETAILS_WORD, TEXT_DETAILS_CHARACTER, TEXT_DETAILS_ALL)]
assert_equal(text_s_detail[0], text_s_detail[1])
assert_equal(text_s_detail[1], text_s_detail[2])
assert_equal(text_s_detail[2], text_s_detail[3])
assert_equal(
text_s_detail[0],
Expression(
[Symbol('page'), 0, 0, 2550, 3300,
'2 Hyperlinks \n'
'2.1 local \n' +
u('→1 \n') +
'2.2 remote \nhttp://jwilk.net/ \n'
'2 \n'
]
)
)
assert_equal(
text_s_detail[4],
Expression(
[Symbol('page'), 0, 0, 2550, 3300,
[Symbol('line'), 462, 2712, 910, 2777, '2 Hyperlinks '],
[Symbol('line'), 462, 2599, 714, 2641, '2.1 local '],
[Symbol('line'), 464, 2505, 544, 2540, u('→1 ')],
[Symbol('line'), 462, 2358, 772, 2400, '2.2 remote '],
[Symbol('line'), 463, 2256, 964, 2298, 'http://jwilk.net/ '],
[Symbol('line'), 1260, 375, 1282, 409, '2 ']
]
)
)
assert_equal(text_s_detail[5], text_s)
assert_equal(text_s_detail[6], text_s)
assert_equal(text_s_detail[7], text_s)
assert_equal(
text_s,
Expression(
[Symbol('page'), 0, 0, 2550, 3300,
[Symbol('line'), 462, 2712, 910, 2777, [Symbol('word'), 462, 2727, 495, 2776, '2'], [Symbol('word'), 571, 2712, 910, 2777, 'Hyperlinks']],
[Symbol('line'), 462, 2599, 714, 2641, [Symbol('word'), 462, 2599, 532, 2641, '2.1'], [Symbol('word'), 597, 2599, 714, 2640, 'local']],
[Symbol('line'), 464, 2505, 544, 2540, [Symbol('word'), 464, 2505, 544, 2540, u('→1')]],
[Symbol('line'), 462, 2358, 772, 2400, [Symbol('word'), 462, 2358, 535, 2400, '2.2'], [Symbol('word'), 598, 2358, 772, 2397, 'remote']],
[Symbol('line'), 463, 2256, 964, 2298, [Symbol('word'), 463, 2256, 964, 2298, 'http://jwilk.net/']],
[Symbol('line'), 1260, 375, 1282, 409, [Symbol('word'), 1260, 375, 1282, 409, '2']]
]
)
)
with assert_raises_str(TypeError, 'details must be a symbol or none'):
PageText(page, 'eggs')
with assert_raises_str(ValueError, 'details must be equal to TEXT_DETAILS_PAGE, or TEXT_DETAILS_COLUMN, or TEXT_DETAILS_REGION, or TEXT_DETAILS_PARAGRAPH, or TEXT_DETAILS_LINE, or TEXT_DETAILS_WORD, or TEXT_DETAILS_CHARACTER or TEXT_DETAILS_ALL'):
PageText(page, Symbol('eggs'))
