Skip to content

test_pdfconverter

Test conversion of pdf files.

TestPDF2XMLConverter

Bases: XMLTester

Test the class that converts from pdf2xml to giellatekno/divvun xml.

Source code in corpustools/test/test_pdfconverter.py 
328
329
330
331
332
333
334
335
336
337
338
class TestPDF2XMLConverter(xmltester.XMLTester):
    """Test the class that converts from pdf2xml to giellatekno/divvun xml."""

    def test_pdf_converter(self):
        pdfdocument = pdfconverter.PDF2XMLConverter(
            Path(HERE) / "converter_data/fakecorpus/orig/sme/riddu/pdf-test.pdf"
        )
        got = pdfdocument.convert2intermediate()
        want = etree.parse(os.path.join(HERE, "converter_data/pdf-xml2pdf-test.xml"))

        self.assertXmlEqual(got, want)

TestPDFPage

Bases: XMLTester

Source code in corpustools/test/test_pdfconverter.py 
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
class TestPDFPage(xmltester.XMLTester):
    def test_is_inside_margins1(self):
        """top and left inside margins."""
        t = etree.fromstring('<p style="top:109px;left:135px"/>')
        margins = {}
        margins["left_margin"] = 62
        margins["right_margin"] = 802
        margins["top_margin"] = 88
        margins["bottom_margin"] = 1174

        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
        )

        assert p2x.is_inside_margins(t, margins)

    def test_is_inside_margins2(self):
        """top above top margin and left inside margins."""
        t = etree.fromstring('<p style="top:85px;left:135px"/>')
        margins = {}
        margins["left_margin"] = 62
        margins["right_margin"] = 802
        margins["top_margin"] = 88
        margins["bottom_margin"] = 1174

        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
        )

        assert not p2x.is_inside_margins(t, margins)

    def test_is_inside_margins3(self):
        """top below bottom margin and left inside margins."""
        t = etree.fromstring('<p style="top:1178px;left:135px"/>')
        margins = {}
        margins["left_margin"] = 62
        margins["right_margin"] = 802
        margins["top_margin"] = 88
        margins["bottom_margin"] = 1174

        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
        )

        assert not p2x.is_inside_margins(t, margins)

    def test_is_inside_margins4(self):
        """top inside margins and left outside right margin."""
        t = etree.fromstring('<p style="top:1000px;left:50px"/>')
        margins = {}
        margins["left_margin"] = 62
        margins["right_margin"] = 802
        margins["top_margin"] = 88
        margins["bottom_margin"] = 1174

        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
        )

        assert not p2x.is_inside_margins(t, margins)

    def test_is_inside_margins5(self):
        """top inside margins and left outside left margin."""
        t = etree.fromstring('<p style="top:1000px;left:805px"/>')
        margins = {}
        margins["left_margin"] = 62
        margins["right_margin"] = 802
        margins["top_margin"] = 88
        margins["bottom_margin"] = 1174

        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
        )

        assert not p2x.is_inside_margins(t, margins)

    def test_is_skip_page_1(self):
        """Odd page should be skipped when odd is in skip_pages."""
        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page1-div" style="width:862px;height:1263px"/>')
        )

        p2x.is_skip_page(["odd"])

    def test_is_skip_page_2(self):
        """Even page should be skipped when even is in skip_pages."""
        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
        )

        assert p2x.is_skip_page(["even"])

    def test_is_skip_page_3(self):
        """Even page should not be skipped when odd is in skip_pages."""
        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
        )

        assert not p2x.is_skip_page(["odd"])

    def test_is_skip_page_4(self):
        """Odd page should not be skipped when even is in skip_pages."""
        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page1-div" style="width:862px;height:1263px"/>')
        )

        assert not p2x.is_skip_page(["even"])

    def test_is_skip_page_5(self):
        """Page should not be skipped when not in skip_range."""
        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page1-div" style="width:862px;height:1263px"/>')
        )

        assert not p2x.is_skip_page(["even", 3])

    def test_is_skip_page_6(self):
        """Page should be skipped when in skip_range."""
        p2x = pdfconverter.PDFPage(
            etree.fromstring('<div id="page3-div" style="width:862px;height:1263px"/>')
        )

        assert p2x.is_skip_page(["even", 3])

test_is_inside_margins1()

top and left inside margins.

Source code in corpustools/test/test_pdfconverter.py 
204
205
206
207
208
209
210
211
212
213
214
215
216
217
def test_is_inside_margins1(self):
    """top and left inside margins."""
    t = etree.fromstring('<p style="top:109px;left:135px"/>')
    margins = {}
    margins["left_margin"] = 62
    margins["right_margin"] = 802
    margins["top_margin"] = 88
    margins["bottom_margin"] = 1174

    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
    )

    assert p2x.is_inside_margins(t, margins)

test_is_inside_margins2()

top above top margin and left inside margins.

Source code in corpustools/test/test_pdfconverter.py 
219
220
221
222
223
224
225
226
227
228
229
230
231
232
def test_is_inside_margins2(self):
    """top above top margin and left inside margins."""
    t = etree.fromstring('<p style="top:85px;left:135px"/>')
    margins = {}
    margins["left_margin"] = 62
    margins["right_margin"] = 802
    margins["top_margin"] = 88
    margins["bottom_margin"] = 1174

    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
    )

    assert not p2x.is_inside_margins(t, margins)

test_is_inside_margins3()

top below bottom margin and left inside margins.

Source code in corpustools/test/test_pdfconverter.py 
234
235
236
237
238
239
240
241
242
243
244
245
246
247
def test_is_inside_margins3(self):
    """top below bottom margin and left inside margins."""
    t = etree.fromstring('<p style="top:1178px;left:135px"/>')
    margins = {}
    margins["left_margin"] = 62
    margins["right_margin"] = 802
    margins["top_margin"] = 88
    margins["bottom_margin"] = 1174

    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
    )

    assert not p2x.is_inside_margins(t, margins)

test_is_inside_margins4()

top inside margins and left outside right margin.

Source code in corpustools/test/test_pdfconverter.py 
249
250
251
252
253
254
255
256
257
258
259
260
261
262
def test_is_inside_margins4(self):
    """top inside margins and left outside right margin."""
    t = etree.fromstring('<p style="top:1000px;left:50px"/>')
    margins = {}
    margins["left_margin"] = 62
    margins["right_margin"] = 802
    margins["top_margin"] = 88
    margins["bottom_margin"] = 1174

    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
    )

    assert not p2x.is_inside_margins(t, margins)

test_is_inside_margins5()

top inside margins and left outside left margin.

Source code in corpustools/test/test_pdfconverter.py 
264
265
266
267
268
269
270
271
272
273
274
275
276
277
def test_is_inside_margins5(self):
    """top inside margins and left outside left margin."""
    t = etree.fromstring('<p style="top:1000px;left:805px"/>')
    margins = {}
    margins["left_margin"] = 62
    margins["right_margin"] = 802
    margins["top_margin"] = 88
    margins["bottom_margin"] = 1174

    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
    )

    assert not p2x.is_inside_margins(t, margins)

test_is_skip_page_1()

Odd page should be skipped when odd is in skip_pages.

Source code in corpustools/test/test_pdfconverter.py 
279
280
281
282
283
284
285
def test_is_skip_page_1(self):
    """Odd page should be skipped when odd is in skip_pages."""
    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page1-div" style="width:862px;height:1263px"/>')
    )

    p2x.is_skip_page(["odd"])

test_is_skip_page_2()

Even page should be skipped when even is in skip_pages.

Source code in corpustools/test/test_pdfconverter.py 
287
288
289
290
291
292
293
def test_is_skip_page_2(self):
    """Even page should be skipped when even is in skip_pages."""
    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
    )

    assert p2x.is_skip_page(["even"])

test_is_skip_page_3()

Even page should not be skipped when odd is in skip_pages.

Source code in corpustools/test/test_pdfconverter.py 
295
296
297
298
299
300
301
def test_is_skip_page_3(self):
    """Even page should not be skipped when odd is in skip_pages."""
    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page2-div" style="width:862px;height:1263px"/>')
    )

    assert not p2x.is_skip_page(["odd"])

test_is_skip_page_4()

Odd page should not be skipped when even is in skip_pages.

Source code in corpustools/test/test_pdfconverter.py 
303
304
305
306
307
308
309
def test_is_skip_page_4(self):
    """Odd page should not be skipped when even is in skip_pages."""
    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page1-div" style="width:862px;height:1263px"/>')
    )

    assert not p2x.is_skip_page(["even"])

test_is_skip_page_5()

Page should not be skipped when not in skip_range.

Source code in corpustools/test/test_pdfconverter.py 
311
312
313
314
315
316
317
def test_is_skip_page_5(self):
    """Page should not be skipped when not in skip_range."""
    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page1-div" style="width:862px;height:1263px"/>')
    )

    assert not p2x.is_skip_page(["even", 3])

test_is_skip_page_6()

Page should be skipped when in skip_range.

Source code in corpustools/test/test_pdfconverter.py 
319
320
321
322
323
324
325
def test_is_skip_page_6(self):
    """Page should be skipped when in skip_range."""
    p2x = pdfconverter.PDFPage(
        etree.fromstring('<div id="page3-div" style="width:862px;height:1263px"/>')
    )

    assert p2x.is_skip_page(["even", 3])

TestPDFPageMetaData

Bases: TestCase

Source code in corpustools/test/test_pdfconverter.py 
 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
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
class TestPDFPageMetaData(unittest.TestCase):
    def test_compute_default_margins(self):
        """Test that original margins are kept by default."""
        page1 = pdfconverter.PDFPageMetadata(
            page_id="page1-div", page_style="height:1263px;width:862px;"
        )

        assert page1.compute_margins() == {
            "left_margin": 0,
            "right_margin": 862,
            "top_margin": 0,
            "bottom_margin": 1263,
        }

    def test_compute_margins1(self):
        """Test parse_margin_lines."""
        metadata = xslsetter.MetadataHandler("test.pdf.xsl", create=True)
        metadata.set_variable("left_margin", "7=5")
        metadata.set_variable("right_margin", "odd=10,even=15,3=5")
        metadata.set_variable("top_margin", "8=8")
        metadata.set_variable("bottom_margin", "9=20")

        page1 = pdfconverter.PDFPageMetadata(
            page_id="page1-div",
            page_style="height:1263px;width:862px;",
            metadata_margins=metadata.margins,
        )

        assert page1.compute_margins() == {
            "left_margin": 0,
            "right_margin": 775,
            "top_margin": 0,
            "bottom_margin": 1263,
        }

        page2 = pdfconverter.PDFPageMetadata(
            page_id="page2-div",
            page_style="height:1263px;width:862px;",
            metadata_margins=metadata.margins,
        )
        assert page2.compute_margins() == {
            "left_margin": 00,
            "right_margin": 732,
            "top_margin": 0,
            "bottom_margin": 1263,
        }
        page3 = pdfconverter.PDFPageMetadata(
            page_id="page3-div",
            page_style="height:1263px;width:862px;",
            metadata_margins=metadata.margins,
        )
        assert page3.compute_margins() == {
            "left_margin": 0,
            "right_margin": 818,
            "top_margin": 0,
            "bottom_margin": 1263,
        }
        page7 = pdfconverter.PDFPageMetadata(
            page_id="page7-div",
            page_style="height:1263px;width:862px;",
            metadata_margins=metadata.margins,
        )
        assert page7.compute_margins() == {
            "left_margin": 43,
            "right_margin": 775,
            "top_margin": 0,
            "bottom_margin": 1263,
        }
        page8 = pdfconverter.PDFPageMetadata(
            page_id="page8-div",
            page_style="height:1263px;width:862px;",
            metadata_margins=metadata.margins,
        )
        assert page8.compute_margins() == {
            "left_margin": 0,
            "right_margin": 732,
            "top_margin": 101,
            "bottom_margin": 1263,
        }
        page9 = pdfconverter.PDFPageMetadata(
            page_id="page9-div",
            page_style="height:1263px;width:862px;",
            metadata_margins=metadata.margins,
        )
        assert page9.compute_margins() == {
            "left_margin": 0,
            "right_margin": 775,
            "top_margin": 0,
            "bottom_margin": 1010,
        }

    def test_compute_inner_margins_1(self):
        """Test if inner margins is set for the specified page."""
        metadata = xslsetter.MetadataHandler("test.pdf.xsl", create=True)
        metadata.set_variable("inner_top_margin", "1=40")
        metadata.set_variable("inner_bottom_margin", "1=40")

        page1 = pdfconverter.PDFPageMetadata(
            page_id="page1-div",
            page_style="height:1263px;width:862px;",
            metadata_inner_margins=metadata.inner_margins,
        )

        assert page1.compute_inner_margins() == {
            "top_margin": 505,
            "bottom_margin": 757,
            "left_margin": 0,
            "right_margin": 862,
        }

    def test_compute_inner_margins_2(self):
        """Test that inner margins is empty for the specified page."""
        metadata = xslsetter.MetadataHandler("test.pdf.xsl", create=True)
        metadata.set_variable("inner_top_margin", "1=40")
        metadata.set_variable("inner_bottom_margin", "1=40")

        page1 = pdfconverter.PDFPageMetadata(
            page_id="page2-div",
            page_style="height:1263px;width:862px;",
            metadata_inner_margins=metadata.inner_margins,
        )

        assert page1.compute_inner_margins() == {}

    def test_width(self):
        page = pdfconverter.PDFPageMetadata(
            page_id="page1-div", page_style="height:1263px;width:862px;"
        )

        assert page.page_number == 1
        assert page.page_height == 1263
        assert page.page_width == 862

test_compute_default_margins()

Test that original margins are kept by default.

Source code in corpustools/test/test_pdfconverter.py 
70
71
72
73
74
75
76
77
78
79
80
81
def test_compute_default_margins(self):
    """Test that original margins are kept by default."""
    page1 = pdfconverter.PDFPageMetadata(
        page_id="page1-div", page_style="height:1263px;width:862px;"
    )

    assert page1.compute_margins() == {
        "left_margin": 0,
        "right_margin": 862,
        "top_margin": 0,
        "bottom_margin": 1263,
    }

test_compute_inner_margins_1()

Test if inner margins is set for the specified page.

Source code in corpustools/test/test_pdfconverter.py 
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
def test_compute_inner_margins_1(self):
    """Test if inner margins is set for the specified page."""
    metadata = xslsetter.MetadataHandler("test.pdf.xsl", create=True)
    metadata.set_variable("inner_top_margin", "1=40")
    metadata.set_variable("inner_bottom_margin", "1=40")

    page1 = pdfconverter.PDFPageMetadata(
        page_id="page1-div",
        page_style="height:1263px;width:862px;",
        metadata_inner_margins=metadata.inner_margins,
    )

    assert page1.compute_inner_margins() == {
        "top_margin": 505,
        "bottom_margin": 757,
        "left_margin": 0,
        "right_margin": 862,
    }

test_compute_inner_margins_2()

Test that inner margins is empty for the specified page.

Source code in corpustools/test/test_pdfconverter.py 
179
180
181
182
183
184
185
186
187
188
189
190
191
def test_compute_inner_margins_2(self):
    """Test that inner margins is empty for the specified page."""
    metadata = xslsetter.MetadataHandler("test.pdf.xsl", create=True)
    metadata.set_variable("inner_top_margin", "1=40")
    metadata.set_variable("inner_bottom_margin", "1=40")

    page1 = pdfconverter.PDFPageMetadata(
        page_id="page2-div",
        page_style="height:1263px;width:862px;",
        metadata_inner_margins=metadata.inner_margins,
    )

    assert page1.compute_inner_margins() == {}

test_compute_margins1()

Test parse_margin_lines.

Source code in corpustools/test/test_pdfconverter.py 
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
def test_compute_margins1(self):
    """Test parse_margin_lines."""
    metadata = xslsetter.MetadataHandler("test.pdf.xsl", create=True)
    metadata.set_variable("left_margin", "7=5")
    metadata.set_variable("right_margin", "odd=10,even=15,3=5")
    metadata.set_variable("top_margin", "8=8")
    metadata.set_variable("bottom_margin", "9=20")

    page1 = pdfconverter.PDFPageMetadata(
        page_id="page1-div",
        page_style="height:1263px;width:862px;",
        metadata_margins=metadata.margins,
    )

    assert page1.compute_margins() == {
        "left_margin": 0,
        "right_margin": 775,
        "top_margin": 0,
        "bottom_margin": 1263,
    }

    page2 = pdfconverter.PDFPageMetadata(
        page_id="page2-div",
        page_style="height:1263px;width:862px;",
        metadata_margins=metadata.margins,
    )
    assert page2.compute_margins() == {
        "left_margin": 00,
        "right_margin": 732,
        "top_margin": 0,
        "bottom_margin": 1263,
    }
    page3 = pdfconverter.PDFPageMetadata(
        page_id="page3-div",
        page_style="height:1263px;width:862px;",
        metadata_margins=metadata.margins,
    )
    assert page3.compute_margins() == {
        "left_margin": 0,
        "right_margin": 818,
        "top_margin": 0,
        "bottom_margin": 1263,
    }
    page7 = pdfconverter.PDFPageMetadata(
        page_id="page7-div",
        page_style="height:1263px;width:862px;",
        metadata_margins=metadata.margins,
    )
    assert page7.compute_margins() == {
        "left_margin": 43,
        "right_margin": 775,
        "top_margin": 0,
        "bottom_margin": 1263,
    }
    page8 = pdfconverter.PDFPageMetadata(
        page_id="page8-div",
        page_style="height:1263px;width:862px;",
        metadata_margins=metadata.margins,
    )
    assert page8.compute_margins() == {
        "left_margin": 0,
        "right_margin": 732,
        "top_margin": 101,
        "bottom_margin": 1263,
    }
    page9 = pdfconverter.PDFPageMetadata(
        page_id="page9-div",
        page_style="height:1263px;width:862px;",
        metadata_margins=metadata.margins,
    )
    assert page9.compute_margins() == {
        "left_margin": 0,
        "right_margin": 775,
        "top_margin": 0,
        "bottom_margin": 1010,
    }

test_merge_children_of_p(test_input, expected)

Test merging of two xml files.

Source code in corpustools/test/test_pdfconverter.py 
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
@pytest.mark.parametrize(
    ("test_input", "expected"),
    [
        (
            "<p><i>toobdast  </i>  <i>jeä</i><i>ʹrben</i>    alggmeeraid </p>",
            "<p><i>toobdast    jeäʹrben</i>    alggmeeraid </p>",
        ),
        (
            "<p><b>toobdast  </b>  <i>jeä</i><i>ʹrben</i>    alggmeeraid </p>",
            "<p><b>toobdast  </b>  <i>jeäʹrben</i>    alggmeeraid </p>",
        ),
        (
            "<p><i>toobdast  </i>  <i>jeä</i><b>ʹrben</b>    alggmeeraid </p>",
            "<p><i>toobdast    jeä</i><b>ʹrben</b>    alggmeeraid </p>",
        ),
    ],
)
def test_merge_children_of_p(test_input: str, expected: str):
    """Test merging of two xml files."""

    assert (
        etree.tostring(
            pdfconverter.merge_children_of_p(etree.fromstring(test_input)),
            encoding="unicode",
        )
        == expected
    )