From e03f4eda875f4a36a3d3e62eac467b3f2b1e0fbe Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Wed, 17 Jun 2020 18:03:01 -0700
Subject: rename pdf tools to pdfextract

---
 python/tests/test_pdf.py        | 61 -----------------------------------------
 python/tests/test_pdfextract.py | 61 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+), 61 deletions(-)
 delete mode 100644 python/tests/test_pdf.py
 create mode 100644 python/tests/test_pdfextract.py

(limited to 'python/tests')

diff --git a/python/tests/test_pdf.py b/python/tests/test_pdf.py
deleted file mode 100644
index 1ccf85c..0000000
--- a/python/tests/test_pdf.py
+++ /dev/null
@@ -1,61 +0,0 @@
-
-import pytest
-import struct
-import responses
-
-from sandcrawler import PdfExtractWorker, PdfExtractBlobWorker, CdxLinePusher, BlackholeSink, WaybackClient
-from sandcrawler.pdf import process_pdf
-from test_wayback import wayback_client, cdx_client
-
-
-FAKE_PDF_BYTES = b"%PDF SOME JUNK" + struct.pack("!q", 112853843)
-
-def test_process_fake_pdf():
-    resp = process_pdf(FAKE_PDF_BYTES)
-    print(resp)
-    assert resp.status == "not-pdf"
-
-def test_process_dummy_pdf():
-    with open('tests/files/dummy.pdf', 'rb') as f:
-        pdf_bytes = f.read()
-    resp = process_pdf(pdf_bytes)
-    assert resp.status == 'success'
-    assert resp.page0_thumbnail is not None
-    assert len(resp.text) > 10
-    assert resp.meta_xml is None
-    assert resp.file_meta['mimetype'] == 'application/pdf'
-    print(resp.pdf_info)
-    print(resp.pdf_extra)
-    assert resp.pdf_info['Author'] == "Evangelos Vlachogiannis"
-    # 595 x 842
-    assert resp.pdf_extra['height'] == 842
-    assert resp.pdf_extra['width'] == 595
-    assert resp.pdf_extra['page_count'] == 1
-
-def test_pdfextract_worker_cdx(wayback_client):
-
-    sink = BlackholeSink()
-    worker = PdfExtractWorker(wayback_client, sink=sink, thumbnail_sink=sink)
-
-    with open('tests/files/example.cdx', 'r') as cdx_file:
-        pusher = CdxLinePusher(
-            worker,
-            cdx_file,
-            filter_http_statuses=[200, 226],
-            filter_mimetypes=['application/pdf'],
-        )
-        pusher_counts = pusher.run()
-        assert pusher_counts['total']
-        assert pusher_counts['pushed'] == 7
-        assert pusher_counts['pushed'] == worker.counts['total']
-
-def test_pdfextract_blob_worker():
-
-    sink = BlackholeSink()
-    worker = PdfExtractBlobWorker(sink=sink, thumbnail_sink=sink)
-
-    with open('tests/files/dummy.pdf', 'rb') as f:
-        pdf_bytes = f.read()
-
-    worker.process(pdf_bytes)
-
diff --git a/python/tests/test_pdfextract.py b/python/tests/test_pdfextract.py
new file mode 100644
index 0000000..1ccf85c
--- /dev/null
+++ b/python/tests/test_pdfextract.py
@@ -0,0 +1,61 @@
+
+import pytest
+import struct
+import responses
+
+from sandcrawler import PdfExtractWorker, PdfExtractBlobWorker, CdxLinePusher, BlackholeSink, WaybackClient
+from sandcrawler.pdf import process_pdf
+from test_wayback import wayback_client, cdx_client
+
+
+FAKE_PDF_BYTES = b"%PDF SOME JUNK" + struct.pack("!q", 112853843)
+
+def test_process_fake_pdf():
+    resp = process_pdf(FAKE_PDF_BYTES)
+    print(resp)
+    assert resp.status == "not-pdf"
+
+def test_process_dummy_pdf():
+    with open('tests/files/dummy.pdf', 'rb') as f:
+        pdf_bytes = f.read()
+    resp = process_pdf(pdf_bytes)
+    assert resp.status == 'success'
+    assert resp.page0_thumbnail is not None
+    assert len(resp.text) > 10
+    assert resp.meta_xml is None
+    assert resp.file_meta['mimetype'] == 'application/pdf'
+    print(resp.pdf_info)
+    print(resp.pdf_extra)
+    assert resp.pdf_info['Author'] == "Evangelos Vlachogiannis"
+    # 595 x 842
+    assert resp.pdf_extra['height'] == 842
+    assert resp.pdf_extra['width'] == 595
+    assert resp.pdf_extra['page_count'] == 1
+
+def test_pdfextract_worker_cdx(wayback_client):
+
+    sink = BlackholeSink()
+    worker = PdfExtractWorker(wayback_client, sink=sink, thumbnail_sink=sink)
+
+    with open('tests/files/example.cdx', 'r') as cdx_file:
+        pusher = CdxLinePusher(
+            worker,
+            cdx_file,
+            filter_http_statuses=[200, 226],
+            filter_mimetypes=['application/pdf'],
+        )
+        pusher_counts = pusher.run()
+        assert pusher_counts['total']
+        assert pusher_counts['pushed'] == 7
+        assert pusher_counts['pushed'] == worker.counts['total']
+
+def test_pdfextract_blob_worker():
+
+    sink = BlackholeSink()
+    worker = PdfExtractBlobWorker(sink=sink, thumbnail_sink=sink)
+
+    with open('tests/files/dummy.pdf', 'rb') as f:
+        pdf_bytes = f.read()
+
+    worker.process(pdf_bytes)
+
-- 
cgit v1.2.3