Include tests in the sdist tarball

9 files changed, 294 insertions, 0 deletions

diff --git a/test/run.sh b/test/run.sh
new file mode 100755
index 0000000..3768497
--- /dev/null
+++ b/test/run.sh
@@ -0,0 +1,12 @@
+#!/bin/sh
+
+set -e
+
+# ensure we can use unicode filenames in the test
+export LC_ALL=en_US.UTF-8
+THISDIR=`dirname $0`
+export PYTHONPATH=${THISDIR}/..
+
+python2.6 ${THISDIR}/test.py
+python2.7 ${THISDIR}/test.py
+python3 ${THISDIR}/test.py
diff --git a/test/test.py b/test/test.py
new file mode 100644
index 0000000..f9c9c41
--- /dev/null
+++ b/test/test.py
@@ -0,0 +1,78 @@
+import os.path
+import unittest
+
+import magic
+
+class MagicTest(unittest.TestCase):
+    TESTDATA_DIR = os.path.join(os.path.dirname(__file__), 'testdata')
+
+    def assert_values(self, m, expected_values):
+        for filename, expected_value in expected_values.items():
+            try:
+                filename = os.path.join(self.TESTDATA_DIR, filename)
+            except TypeError:
+                filename = os.path.join(self.TESTDATA_DIR.encode('utf-8'), filename)
+
+            with open(filename, 'rb') as f:
+                value = m.from_buffer(f.read())
+                expected_value_bytes = expected_value.encode('utf-8')
+                self.assertEqual(value, expected_value_bytes)
+
+            value = m.from_file(filename)
+            self.assertEqual(value, expected_value_bytes)
+        
+    def test_mime_types(self):
+        m = magic.Magic(mime=True)
+        self.assert_values(m, {
+            'magic.pyc': 'application/octet-stream',
+            'test.pdf': 'application/pdf',
+            'test.gz': 'application/x-gzip',
+            'text.txt': 'text/plain',
+            b'\xce\xbb'.decode('utf-8'): 'text/plain',
+            b'\xce\xbb': 'text/plain',
+        })
+
+    def test_descriptions(self):
+        m = magic.Magic()
+        os.environ['TZ'] = 'UTC'  # To get the last modified date of test.gz in UTC
+        try:
+            self.assert_values(m, {
+                'magic.pyc': 'python 2.4 byte-compiled',
+                'test.pdf': 'PDF document, version 1.2',
+                'test.gz': 'gzip compressed data, was "test", from Unix, '
+                           'last modified: Sun Jun 29 01:32:52 2008',
+                'text.txt': 'ASCII text',
+            })
+        finally:
+            del os.environ['TZ']
+
+    def test_mime_encodings(self):
+        m = magic.Magic(mime_encoding=True)
+        self.assert_values(m, {
+            'text-iso8859-1.txt': 'iso-8859-1',
+            'text.txt': 'us-ascii',
+        })
+
+    def test_errors(self):
+        m = magic.Magic()
+        self.assertRaises(IOError, m.from_file, 'nonexistent')
+        self.assertRaises(magic.MagicException, magic.Magic,
+                          magic_file='nonexistent')
+        os.environ['MAGIC'] = 'nonexistent'
+        try:
+            self.assertRaises(magic.MagicException, magic.Magic)
+        finally:
+            del os.environ['MAGIC']
+
+    def test_keep_going(self):
+        filename = os.path.join(self.TESTDATA_DIR, 'keep-going.jpg')
+
+        m = magic.Magic(mime=True)
+        self.assertEqual(m.from_file(filename), 
+                         'application/octet-stream'.encode('utf-8'))
+        
+        m = magic.Magic(mime=True, keep_going=True)
+        self.assertEqual(m.from_file(filename), 'image/jpeg'.encode('utf-8'))
+
+if __name__ == '__main__':
+    unittest.main()
diff --git a/test/testdata/keep-going.jpg b/test/testdata/keep-going.jpg
new file mode 100644
index 0000000..c15171d
--- /dev/null
+++ b/test/testdata/keep-going.jpg
diff --git a/test/testdata/magic.pyc b/test/testdata/magic.pyc
new file mode 100644
index 0000000..ba801e0
--- /dev/null
+++ b/test/testdata/magic.pyc
diff --git a/test/testdata/test.gz b/test/testdata/test.gz
new file mode 100644
index 0000000..5d847dd
--- /dev/null
+++ b/test/testdata/test.gz
diff --git a/test/testdata/test.pdf b/test/testdata/test.pdf
new file mode 100644
index 0000000..b986617
--- /dev/null
+++ b/test/testdata/test.pdf
@@ -0,0 +1,199 @@
+%PDF-1.2
+7 0 obj
+[5 0 R/XYZ 111.6 757.86]
+endobj
+13 0 obj
+<<
+/Title(About this document)
+/A<<
+/S/GoTo
+/D(subsection.1.1)
+>>
+/Parent 12 0 R
+/Next 14 0 R
+>>
+endobj
+15 0 obj
+<<
+/Title(Compiling with GHC)
+/A<<
+/S/GoTo
+/D(subsubsection.1.2.1)
+>>
+/Parent 14 0 R
+/Next 16 0 R
+>>
+endobj
+16 0 obj
+<<
+/Title(Compiling with Hugs)
+/A<<
+/S/GoTo
+/D(subsubsection.1.2.2)
+>>
+/Parent 14 0 R
+/Prev 15 0 R
+>>
+endobj
+14 0 obj
+<<
+/Title(Compatibility)
+/A<<
+/S/GoTo
+/D(subsection.1.2)
+>>
+/Parent 12 0 R
+/Prev 13 0 R
+/First 15 0 R
+/Last 16 0 R
+/Count -2
+/Next 17 0 R
+>>
+endobj
+17 0 obj
+<<
+/Title(Reporting bugs)
+/A<<
+/S/GoTo
+/D(subsection.1.3)
+>>
+/Parent 12 0 R
+/Prev 14 0 R
+/Next 18 0 R
+>>
+endobj
+18 0 obj
+<<
+/Title(History)
+/A<<
+/S/GoTo
+/D(subsection.1.4)
+>>
+/Parent 12 0 R
+/Prev 17 0 R
+/Next 19 0 R
+>>
+endobj
+19 0 obj
+<<
+/Title(License)
+/A<<
+/S/GoTo
+/D(subsection.1.5)
+>>
+/Parent 12 0 R
+/Prev 18 0 R
+>>
+endobj
+12 0 obj
+<<
+/Title(Introduction)
+/A<<
+/S/GoTo
+/D(section.1)
+>>
+/Parent 11 0 R
+/First 13 0 R
+/Last 19 0 R
+/Count -5
+/Next 20 0 R
+>>
+endobj
+21 0 obj
+<<
+/Title(Running a parser)
+/A<<
+/S/GoTo
+/D(subsection.2.1)
+>>
+/Parent 20 0 R
+/Next 22 0 R
+>>
+endobj
+22 0 obj
+<<
+/Title(Sequence and choice)
+/A<<
+/S/GoTo
+/D(subsection.2.2)
+>>
+/Parent 20 0 R
+/Prev 21 0 R
+/Next 23 0 R
+>>
+endobj
+23 0 obj
+<<
+/Title(Predictive parsers)
+/A<<
+/S/GoTo
+/D(subsection.2.3)
+>>
+/Parent 20 0 R
+/Prev 22 0 R
+/Next 24 0 R
+>>
+endobj
+24 0 obj
+<<
+/Title(Adding semantics)
+/A<<
+/S/GoTo
+/D(subsection.2.4)
+>>
+/Parent 20 0 R
+/Prev 23 0 R
+/Next 25 0 R
+>>
+endobj
+25 0 obj
+<<
+/Title(Sequences and seperators)
+/A<<
+/S/GoTo
+/D(subsection.2.5)
+>>
+/Parent 20 0 R
+/Prev 24 0 R
+/Next 26 0 R
+>>
+endobj
+26 0 obj
+<<
+/Title(Improving error messages)
+/A<<
+/S/GoTo
+/D(subsection.2.6)
+>>
+/Parent 20 0 R
+/Prev 25 0 R
+/Next 27 0 R
+>>
+endobj
+27 0 obj
+<<
+/Title(Expressions)
+/A<<
+/S/GoTo
+/D(subsection.2.7)
+>>
+/Parent 20 0 R
+/Prev 26 0 R
+/Next 28 0 R
+>>
+endobj
+28 0 obj
+<<
+/Title(Lexical analysis)
+/A<<
+/S/GoTo
+/D(subsection.2.8)
+>>
+/Parent 20 0 R
+/Prev 27 0 R
+/Next 29 0 R
+>>
+endobj
+30 0 obj
+<<
+/Title(Lexeme parsers
\ No newline at end of file
diff --git a/test/testdata/text-iso8859-1.txt b/test/testdata/text-iso8859-1.txt
new file mode 100644
index 0000000..524a1d0
--- /dev/null
+++ b/test/testdata/text-iso8859-1.txt
@@ -0,0 +1,2 @@
+This is a web page encoded in iso-8859-1
+éèàùôâïî
diff --git a/test/testdata/text.txt b/test/testdata/text.txt
new file mode 100644
index 0000000..476f506
--- /dev/null
+++ b/test/testdata/text.txt
@@ -0,0 +1,2 @@
+Hello, World!
+
diff --git a/test/testdata/λ b/test/testdata/λ
new file mode 100644
index 0000000..9daeafb
--- /dev/null
+++ b/test/testdata/λ
@@ -0,0 +1 @@
+test