diff --git a/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin b/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin
index bef3d5db..934404be 100644
Binary files a/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin and b/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/pdf.bin b/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/pdf.bin
index 480726d5..934404be 100644
Binary files a/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/pdf.bin and b/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/pdf.bin b/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/pdf.bin
index bef3d5db..934404be 100644
Binary files a/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/pdf.bin and b/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/pdf.bin b/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/pdf.bin
index 480726d5..934404be 100644
Binary files a/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/pdf.bin and b/tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/cardinal/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin b/tests/cache/cardinal/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
index e5b2eb08..958c693d 100644
--- a/tests/cache/cardinal/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
+++ b/tests/cache/cardinal/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
The LinnSequencer
diff --git a/tests/cache/cardinal/__-l__eng__000002.ocr.png__000002__hocr__txt/hocr.bin b/tests/cache/cardinal/__-l__eng__000002.ocr.png__000002__hocr__txt/hocr.bin
index 91fc6999..e79348cb 100644
--- a/tests/cache/cardinal/__-l__eng__000002.ocr.png__000002__hocr__txt/hocr.bin
+++ b/tests/cache/cardinal/__-l__eng__000002.ocr.png__000002__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
The LinnSequencer
@@ -18,7 +18,7 @@
-
+
The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
@@ -35,7 +35,8 @@
FORWARD, REWIND, and LOCATE controls.
-
+
+
e Each of the 100 sequences contains 32 simultaneous, polyphonic tracks. Each track may
@@ -43,25 +44,25 @@
-
+
-
+
¢ Ultra-fast 3%” disk drive stores complex songs in seconds and holds over 110,000 notes
-
+
-
+
¢ One or all tracks may be TRANSPOSED at the touch of a key.
@@ -71,31 +72,31 @@
-
+
-
+
¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
-
+
¢ Optional SMPTE time code synchronization.
-
+
© Optional remote control.
-
+
Recording a Sequence
@@ -112,13 +113,13 @@
-
+
corrected! (Timing correction may be adjusted or defeated).
-
+
Any additional notes played will be added into the track
@@ -147,7 +148,7 @@
-
+
Editing
@@ -162,7 +163,7 @@
-
+
added, erased, or changed using the SINGLE STEP func-
@@ -170,13 +171,13 @@
-
+
-
+
simply use LOCATE, FAST FORWARD, or REWIND to
@@ -199,7 +200,7 @@
-
+
Creating a Song
@@ -222,7 +223,7 @@
-
+
Composition Without Compromise
@@ -241,19 +242,19 @@
-
+
* Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
-
+
HELP button displays additional explanations.
-
+
* Non-destructive recording—existing notes are not erased while recording.
@@ -261,25 +262,25 @@
-
+
ERASE, REPEAT, PLAY/STOP, or LOCATE.
-
+
¢ Iwo TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
-
+
© Will sync to standard LinnDrum or Linn 9000 sync tone.
-
+
© Utilizes ultra high-speed, 8 MHz 80186 16 bit computer internally for FAST operation.
@@ -287,25 +288,25 @@
-
+
-
+
¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
-
+
-
+
¢ TEMPO CHANGES may be programmed into a sequence, with smooth transitions if desired.
@@ -313,7 +314,7 @@
-
+
-
+
18720 Oxnard Street, Tarzana, CA 91356
diff --git a/tests/cache/cardinal/__-l__eng__000003.ocr.png__000003__hocr__txt/hocr.bin b/tests/cache/cardinal/__-l__eng__000003.ocr.png__000003__hocr__txt/hocr.bin
index f1a87587..964c45d6 100644
--- a/tests/cache/cardinal/__-l__eng__000003.ocr.png__000003__hocr__txt/hocr.bin
+++ b/tests/cache/cardinal/__-l__eng__000003.ocr.png__000003__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
The LinnSequencer
diff --git a/tests/cache/cardinal/__-l__eng__000004.ocr.png__000004__hocr__txt/hocr.bin b/tests/cache/cardinal/__-l__eng__000004.ocr.png__000004__hocr__txt/hocr.bin
index 86d06f67..bae4dae5 100644
--- a/tests/cache/cardinal/__-l__eng__000004.ocr.png__000004__hocr__txt/hocr.bin
+++ b/tests/cache/cardinal/__-l__eng__000004.ocr.png__000004__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
The LinnSequencer
@@ -18,7 +18,7 @@
-
+
The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
@@ -35,7 +35,8 @@
FORWARD, REWIND, and LOCATE controls.
-
+
+
e Each of the 100 sequences contains 32 simultaneous, polyphonic tracks. Each track may
@@ -43,25 +44,25 @@
-
+
-
+
¢ Ultra-fast 3%” disk drive stores complex songs in seconds and holds over 110,000 notes
-
+
-
+
¢ One or all tracks may be TRANSPOSED at the touch of a key.
@@ -71,31 +72,31 @@
-
+
-
+
¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
-
+
¢ Optional SMPTE time code synchronization.
-
+
© Optional remote control.
-
+
Recording a Sequence
@@ -112,13 +113,13 @@
-
+
corrected! (Timing correction may be adjusted or defeated).
-
+
Any additional notes played will be added into the track
@@ -147,7 +148,7 @@
-
+
Editing
@@ -162,7 +163,7 @@
-
+
added, erased, or changed using the SINGLE STEP func-
@@ -170,13 +171,13 @@
-
+
-
+
simply use LOCATE, FAST FORWARD, or REWIND to
@@ -199,7 +200,7 @@
-
+
Creating a Song
@@ -222,7 +223,7 @@
-
+
Composition Without Compromise
@@ -241,19 +242,19 @@
-
+
* Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
-
+
HELP button displays additional explanations.
-
+
* Non-destructive recording—existing notes are not erased while recording.
@@ -261,25 +262,25 @@
-
+
ERASE, REPEAT, PLAY/STOP, or LOCATE.
-
+
¢ Iwo TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
-
+
© Will sync to standard LinnDrum or Linn 9000 sync tone.
-
+
© Utilizes ultra high-speed, 8 MHz 80186 16 bit computer internally for FAST operation.
@@ -287,25 +288,25 @@
-
+
-
+
¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
-
+
-
+
¢ TEMPO CHANGES may be programmed into a sequence, with smooth transitions if desired.
@@ -313,7 +314,7 @@
-
+
-
+
18720 Oxnard Street, Tarzana, CA 91356
diff --git a/tests/cache/ccitt/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin b/tests/cache/ccitt/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin
index 8707e513..af8048b3 100644
Binary files a/tests/cache/ccitt/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin and b/tests/cache/ccitt/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/ccitt/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin b/tests/cache/ccitt/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
index 895d4f7d..60f1b823 100644
--- a/tests/cache/ccitt/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
+++ b/tests/cache/ccitt/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
The LinnSequencer
diff --git a/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin b/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin
new file mode 100644
index 00000000..99136e20
Binary files /dev/null and b/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin b/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
new file mode 100644
index 00000000..80755b10
--- /dev/null
+++ b/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
@@ -0,0 +1,2 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
+OSD: Weak margin (6.83) for 47 blob text block, but using orientation anyway: 0
diff --git a/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stdout.bin b/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stdout.bin
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin b/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin
new file mode 100644
index 00000000..07716963
--- /dev/null
+++ b/tests/cache/cmyk/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin
@@ -0,0 +1,9 @@
+Multicolor Black
+Pure Black (K = 100}
+
+Pure Magenta
+
+Pure Cyan
+
+Pure Yellow
+
\ No newline at end of file
diff --git a/tests/cache/cmyk/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin b/tests/cache/cmyk/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
new file mode 100644
index 00000000..75340751
--- /dev/null
+++ b/tests/cache/cmyk/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
@@ -0,0 +1,41 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Multicolor Black
+
+ Pure Black (K = 100}
+
+
+
+
+
+
+
+
4ist ConGREss, } SENATE. { Ex. Doc,
diff --git a/tests/cache/lichtenstein/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin b/tests/cache/lichtenstein/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin
index 06fba530..802dff6b 100644
Binary files a/tests/cache/lichtenstein/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin and b/tests/cache/lichtenstein/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/lichtenstein/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin b/tests/cache/lichtenstein/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
index 829ca735..e1507b3c 100644
--- a/tests/cache/lichtenstein/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
+++ b/tests/cache/lichtenstein/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
@@ -1,3 +1,2 @@
Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
-Too few characters. Skipping this page
-OSD: Weak margin (0.00) for 17 blob text block, but using orientation anyway: 0
+OSD: Weak margin (1.16) for 27 blob text block, but using orientation anyway: 2
diff --git a/tests/cache/lichtenstein/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin b/tests/cache/lichtenstein/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
index 304079b7..779fccca 100644
--- a/tests/cache/lichtenstein/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
+++ b/tests/cache/lichtenstein/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
@@ -9,10 +9,10 @@
-
-
-
-
+
+
diff --git a/tests/cache/lichtenstein/__-l__eng__000001.ocr.png__000001__hocr__txt/stderr.bin b/tests/cache/lichtenstein/__-l__eng__000001.ocr.png__000001__hocr__txt/stderr.bin
index 829ca735..e1507b3c 100644
--- a/tests/cache/lichtenstein/__-l__eng__000001.ocr.png__000001__hocr__txt/stderr.bin
+++ b/tests/cache/lichtenstein/__-l__eng__000001.ocr.png__000001__hocr__txt/stderr.bin
@@ -1,3 +1,2 @@
Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
-Too few characters. Skipping this page
-OSD: Weak margin (0.00) for 17 blob text block, but using orientation anyway: 0
+OSD: Weak margin (1.16) for 27 blob text block, but using orientation anyway: 2
diff --git a/tests/cache/manifest.jsonl b/tests/cache/manifest.jsonl
index b8bda3d2..4740b435 100644
--- a/tests/cache/manifest.jsonl
+++ b/tests/cache/manifest.jsonl
@@ -1,49 +1,49 @@
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/graph_ocred.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003.ocr.png", "$TMPDIR/000003.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004.ocr.png", "$TMPDIR/000004.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000005.ocr.png", "$TMPDIR/000005.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000006.ocr.png__000006.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000006.ocr.png", "$TMPDIR/000006.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000003.ocr.png__000003__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000003.ocr.png", "$TMPDIR/000003", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000004.ocr.png__000004__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000004.ocr.png", "$TMPDIR/000004", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000003.ocr.png__000003__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000003.ocr.png", "$TMPDIR/000003", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000004.ocr.png__000004__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000004.ocr.png", "$TMPDIR/000004", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000005.ocr.png__000005__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000005.ocr.png", "$TMPDIR/000005", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000005.ocr.png__000005__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000005.ocr.png", "$TMPDIR/000005", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000006.ocr.png__000006__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000006.ocr.png", "$TMPDIR/000006", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000006.ocr.png__000006__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000006.ocr.png", "$TMPDIR/000006", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__fra__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/francais.pdf", "args": ["-l", "fra", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__--psm__7__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__--psm__7__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/2400dpi.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002.ocr.png", "$TMPDIR/000002.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000001.ocr.preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001.ocr.preview.jpg", "stdout"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000003.ocr.preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000003.ocr.preview.jpg", "stdout"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000004.ocr.preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000004.ocr.preview.jpg", "stdout"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000002.ocr.preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000002.ocr.preview.jpg", "stdout"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000004.ocr.png__000004__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000004.ocr.png", "$TMPDIR/000004", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000002.ocr.png__000002__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000002.ocr.png", "$TMPDIR/000002", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000003.ocr.png__000003__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000003.ocr.png", "$TMPDIR/000003", "hocr", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004.ocr.png", "$TMPDIR/000004.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003.ocr.png", "$TMPDIR/000003.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002.ocr.png", "$TMPDIR/000002.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000001.ocr.preview.jpg__stdout", "sourcefile": "resources/poster.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001.ocr.preview.jpg", "stdout"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
-{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.75.3 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.5.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/cmyk.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/cmyk.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/graph_ocred.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004.ocr.png", "$TMPDIR/000004.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003.ocr.png", "$TMPDIR/000003.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000005.ocr.png", "$TMPDIR/000005.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000006.ocr.png__000006.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000006.ocr.png", "$TMPDIR/000006.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000004.ocr.png__000004__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000004.ocr.png", "$TMPDIR/000004", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000003.ocr.png__000003__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000003.ocr.png", "$TMPDIR/000003", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000005.ocr.png", "$TMPDIR/000005.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000006.ocr.png__000006.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000006.ocr.png", "$TMPDIR/000006.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000005.ocr.png__000005__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000005.ocr.png", "$TMPDIR/000005", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000006.ocr.png__000006__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000006.ocr.png", "$TMPDIR/000006", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000006.ocr.png__000006__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000006.ocr.png", "$TMPDIR/000006", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__fra__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/francais.pdf", "args": ["-l", "fra", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__--psm__7__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__--psm__7__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002.ocr.png", "$TMPDIR/000002.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/2400dpi.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000001.ocr.preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001.ocr.preview.jpg", "stdout"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000003.ocr.preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000003.ocr.preview.jpg", "stdout"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000004.ocr.preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000004.ocr.preview.jpg", "stdout"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000002.ocr.preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000002.ocr.preview.jpg", "stdout"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000003.ocr.png__000003__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000003.ocr.png", "$TMPDIR/000003", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000001.ocr.png__000001__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000002.ocr.png__000002__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000002.ocr.png", "$TMPDIR/000002", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__000004.ocr.png__000004__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000004.ocr.png", "$TMPDIR/000004", "hocr", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003.ocr.png", "$TMPDIR/000003.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004.ocr.png", "$TMPDIR/000004.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002.ocr.png", "$TMPDIR/000002.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__osd__--psm__0__000001.ocr.preview.jpg__stdout", "sourcefile": "resources/poster.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001.ocr.preview.jpg", "stdout"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
+{"tesseract_version": "tesseract 4.0.0-beta.1 leptonica-1.76.0 libjpeg 9c : libpng 1.6.34 : libtiff 4.0.9 : zlib 1.2.11 : libopenjp2 2.3.0 Found AVX2 Found AVX Found SSE ", "platform": "Darwin-17.6.0-x86_64-i386-64bit", "python": "3.6.5", "argv_slug": "__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001.ocr.png", "$TMPDIR/000001.text", "pdf", "txt"]}
diff --git a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin
index 863015c1..27ed2770 100644
Binary files a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin and b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/pdf.bin b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/pdf.bin
index d7445e32..e88ee050 100644
Binary files a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/pdf.bin and b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/pdf.bin b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/pdf.bin
index c346de53..ec42a800 100644
Binary files a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/pdf.bin and b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/pdf.bin b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/pdf.bin
index 9f2986f7..9c88b072 100644
Binary files a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/pdf.bin and b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt/pdf.bin b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt/pdf.bin
index d412734f..9883cc03 100644
Binary files a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt/pdf.bin and b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt/txt.bin b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt/txt.bin
index f4fd0829..cac2814d 100644
--- a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt/txt.bin
+++ b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000005.ocr.png__000005.text__pdf__txt/txt.bin
@@ -17,7 +17,7 @@ swallowing up of London and Westminster.
Even the Cock-lane ghost had been laid only a
round dozen of years, after rapping out its mes-
sages, as the spirits of this very year last past
-(supematurally deficient in originality) rapped
+(supernaturally deficient in originality) rapped
out theirs. Mere messages in the earthly order of
events had lately come to the English Crown and
People, from a congress of British subjects in
diff --git a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000006.ocr.png__000006.text__pdf__txt/pdf.bin b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000006.ocr.png__000006.text__pdf__txt/pdf.bin
index 1e6582e4..5014004d 100644
Binary files a/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000006.ocr.png__000006.text__pdf__txt/pdf.bin and b/tests/cache/multipage/__-l__eng__-c__textonly_pdf=1__000006.ocr.png__000006.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/multipage/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin b/tests/cache/multipage/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
index 86b9a0fc..d2978b8d 100644
--- a/tests/cache/multipage/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
+++ b/tests/cache/multipage/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
diff --git a/tests/cache/multipage/__-l__eng__000003.ocr.png__000003__hocr__txt/hocr.bin b/tests/cache/multipage/__-l__eng__000003.ocr.png__000003__hocr__txt/hocr.bin
index b518bf8e..da8d3f79 100644
--- a/tests/cache/multipage/__-l__eng__000003.ocr.png__000003__hocr__txt/hocr.bin
+++ b/tests/cache/multipage/__-l__eng__000003.ocr.png__000003__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
Replacement of "creationism" with "intelligent design"
diff --git a/tests/cache/multipage/__-l__eng__000004.ocr.png__000004__hocr__txt/hocr.bin b/tests/cache/multipage/__-l__eng__000004.ocr.png__000004__hocr__txt/hocr.bin
index bf15afca..895ce761 100644
--- a/tests/cache/multipage/__-l__eng__000004.ocr.png__000004__hocr__txt/hocr.bin
+++ b/tests/cache/multipage/__-l__eng__000004.ocr.png__000004__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
Replacement of "creationism" with "intelligent design"
diff --git a/tests/cache/multipage/__-l__eng__000005.ocr.png__000005__hocr__txt/hocr.bin b/tests/cache/multipage/__-l__eng__000005.ocr.png__000005__hocr__txt/hocr.bin
index 3fde71e6..a9d0a83d 100644
--- a/tests/cache/multipage/__-l__eng__000005.ocr.png__000005__hocr__txt/hocr.bin
+++ b/tests/cache/multipage/__-l__eng__000005.ocr.png__000005__hocr__txt/hocr.bin
@@ -9,155 +9,155 @@
-
-
-
- with a plain face, on the throne of England;
+
+
+
+ with a plain face, on the throne of England;
- there were a king with a large jaw and a queen
+ there were a king with a large jaw and a queen
- with a fair face, on the throne of France. In both
+ with a fair face, on the throne of France. In both
- countries it was clearer than crystal to the lords
+ countries it was clearer than crystal to the lords
- of the State preserves of loaves and fishes, that
+ of the State preserves of loaves and fishes, that
- things in general were settled for ever.
+ things in general were settled for ever.
-
+
- It was the year of Our Lord one thousand
+ It was the year of Our Lord one thousand
- seven hundred and seventy-five. Spiritual reve-
+ seven hundred and seventy-five. Spiritual reve-
- lations were conceded to England at that
+ lations were conceded to England at that
- favoured period, as at this, Mrs. Southcott had
+ favoured period, as at this, Mrs. Southcott had
- recently attained her five-and-twentieth blessed
+ recently attained her five-and-twentieth blessed
- birthday, of whom a prophetic private in the Life
+ birthday, of whom a prophetic private in the Life
- Guards had heralded the sublime appearance by
+ Guards had heralded the sublime appearance by
- announcing that arrangements were made for the
+ announcing that arrangements were made for the
- swallowing up of London and Westminster.
+ swallowing up of London and Westminster.
- Even the Cock-lane ghost had been laid only a
+ Even the Cock-lane ghost had been laid only a
- round dozen of years, after rapping out its mes-
+ round dozen of years, after rapping out its mes-
- sages, as the spirits of this very year last past
+ sages, as the spirits of this very year last past
- (supematurally deficient in originality) rapped
+ (supernaturally deficient in originality) rapped
- out theirs. Mere messages in the earthly order of
+ out theirs. Mere messages in the earthly order of
- events had lately come to the English Crown and
+ events had lately come to the English Crown and
- People, from a congress of British subjects in
+ People, from a congress of British subjects in
- America: which, strange to relate, have proved
+ America: which, strange to relate, have proved
- more important to the human race than any com-
+ more important to the human race than any com-
- munications yet received through any of the
+ munications yet received through any of the
- chickens of the Cock-lane brood.
-
-
-
-
-
- France, less favoured on the whole as to mat-
-
- ters spiritual than her sister of the shield and tri-
-
- dent, rolled with exceeding smoothness down
-
- hill, making paper money and spending it. Under
-
- the guidance of her Christian pastors, she enter-
-
- tained herself, besides, with such humane
-
- achievements as sentencing a youth to have his
-
-
-
-
-
- hands cut off, his tongue torn out with pincers,
-
- and his body burned alive, because he had not
-
- kneeled down in the rain to do honour to a dirty
-
- procession of monks which passed within his
-
- view, at a distance of some fifty or sixty yards. It
-
- is likely enough that, rooted in the woods of
-
- France and Norway, there were growing trees,
-
- when that sufferer was put to death, already
-
- marked by the Woodman, Fate, to come down
-
- and be sawn into boards, to make a certain mov-
-
- able framework with a sack and a knife in it, ter-
-
- rible in history. It is likely enough that in the
-
- rough outhouses of some tillers of the heavy
-
- lands adjacent to Paris, there were sheltered
-
- from the weather that very day, rude carts,
-
- bespattered with rustic mire, snuffed about by
-
- pigs, and roosted in by poultry, which the
-
- Farmer, Death, had already set apart to be his
-
- tumbrils of the Revolution. But that Woodman
-
- and that Farmer, though they work unceasingly,
-
- work silently, and no one heard them as they
-
- went about with muffled tread: the rather, foras-
-
- much as to entertain any suspicion that they
-
- were awake, was to be atheistical and traitorous.
+ chickens of the Cock-lane brood.
-
- In England, there was scarcely an amount of
+
+ France, less favoured on the whole as to mat-
- order and protection to justify much national
+ ters spiritual than her sister of the shield and tri-
- boasting. Daring burglaries by armed men, and
+ dent, rolled with exceeding smoothness down
- highway robberies, took place in the capital
+ hill, making paper money and spending it. Under
- itself every night; families were publicly cau-
+ the guidance of her Christian pastors, she enter-
- tioned not to go out of town without removing
+ tained herself, besides, with such humane
- their furniture to upholsterers' warehouses for
+ achievements as sentencing a youth to have his
- security; the highwayman in the dark was a City
+
+
+
+
+ hands cut off, his tongue torn out with pincers,
- tradesman in the light, and, being recognised and
+ and his body burned alive, because he had not
+
+ kneeled down in the rain to do honour to a dirty
+
+ procession of monks which passed within his
+
+ view, at a distance of some fifty or sixty yards. It
+
+ is likely enough that, rooted in the woods of
+
+ France and Norway, there were growing trees,
+
+ when that sufferer was put to death, already
+
+ marked by the Woodman, Fate, to come down
+
+ and be sawn into boards, to make a certain mov-
+
+ able framework with a sack and a knife in it, ter-
+
+ rible in history. It is likely enough that in the
+
+ rough outhouses of some tillers of the heavy
+
+ lands adjacent to Paris, there were sheltered
+
+ from the weather that very day, rude carts,
+
+ bespattered with rustic mire, snuffed about by
+
+ pigs, and roosted in by poultry, which the
+
+ Farmer, Death, had already set apart to be his
+
+ tumbrils of the Revolution. But that Woodman
+
+ and that Farmer, though they work unceasingly,
+
+ work silently, and no one heard them as they
+
+ went about with muffled tread: the rather, foras-
+
+ much as to entertain any suspicion that they
+
+ were awake, was to be atheistical and traitorous.
+
+
+
+
+
+ In England, there was scarcely an amount of
+
+ order and protection to justify much national
+
+ boasting. Daring burglaries by armed men, and
+
+ highway robberies, took place in the capital
+
+ itself every night; families were publicly cau-
+
+ tioned not to go out of town without removing
+
+ their furniture to upholsterers' warehouses for
+
+ security; the highwayman in the dark was a City
+
+ tradesman in the light, and, being recognised and
diff --git a/tests/cache/multipage/__-l__eng__000005.ocr.png__000005__hocr__txt/txt.bin b/tests/cache/multipage/__-l__eng__000005.ocr.png__000005__hocr__txt/txt.bin
index f4fd0829..cac2814d 100644
--- a/tests/cache/multipage/__-l__eng__000005.ocr.png__000005__hocr__txt/txt.bin
+++ b/tests/cache/multipage/__-l__eng__000005.ocr.png__000005__hocr__txt/txt.bin
@@ -17,7 +17,7 @@ swallowing up of London and Westminster.
Even the Cock-lane ghost had been laid only a
round dozen of years, after rapping out its mes-
sages, as the spirits of this very year last past
-(supematurally deficient in originality) rapped
+(supernaturally deficient in originality) rapped
out theirs. Mere messages in the earthly order of
events had lately come to the English Crown and
People, from a congress of British subjects in
diff --git a/tests/cache/multipage/__-l__eng__000006.ocr.png__000006__hocr__txt/hocr.bin b/tests/cache/multipage/__-l__eng__000006.ocr.png__000006__hocr__txt/hocr.bin
index 933ae670..8a9b49ac 100644
--- a/tests/cache/multipage/__-l__eng__000006.ocr.png__000006__hocr__txt/hocr.bin
+++ b/tests/cache/multipage/__-l__eng__000006.ocr.png__000006__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
with a plain face, on the throne of England;
diff --git a/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin b/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin
index a3f6a21e..a9c97bef 100644
Binary files a/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin and b/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin b/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
index 55bff330..ef6539e7 100644
--- a/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
+++ b/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
@@ -1,3 +1,3 @@
Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
-OSD: Weak margin (2.72) for 1056 blob text block, but using orientation anyway: 0
-Detected 263 diacritics
+OSD: Weak margin (5.18) for 850 blob text block, but using orientation anyway: 0
+Detected 180 diacritics
diff --git a/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin b/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin
index bcfdcd9f..dc29a8a6 100644
--- a/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin
+++ b/tests/cache/palette/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin
@@ -1,57 +1,51 @@
-41st Congress, }
+41st CONGRESS, } SENATE.
3d Session.
MESSAGE
OF THE
-PRESIDENT OF THE UNITED STATES,
-
-COMMUNICATING
+PRESIDENT OF THE UNITED STATES
A copy of regulations for the consular courts of the United States in Japan,
decreed and issued by the minister of the United States in that country.
-JaNvany 2, 1871.—Read, referred to the Committee on Commerce, and ordered to be
-printed.
+Janvary 27, 1871—Read, referred to the Committee on Commerce, and ordered to be
+printed,
To the Senate and House of Representatives :
I transmit herewith, for the consideration of Congress, a report from
the Secretary of State, and the papers which accompanied it, concern-
-ing regulations for the consular courts of the United States in Ja,
+ing regulations for the consular courts of the United States in Ja
-U. 8. GRANT,
+U. 8. GRAN
WASHINGTON, January 27, 1871.
DEPARTMENT OF STATE,
-Washington, January 26, 1870,
-
-The Seeretary of State has the honor to submit herewith, for revision
+Washington, January 26, 1870.
+The Secretary of State has the honor to submit herewith, for revision
by Congress, in conformity with the provisions of section 6 of the act
approved 22d of June, 1860, a copy of “regulations for the consular
courts of the United States in Japan,” decreed and issued by C. E.
De Long, the minister of the United States in that country, in Septem-
ber, 1870; and also the papers mentioned in the subjoined list, which
-contain suggestions on the subject thereof.
-
-A copy of Art XX-VI of the consular regulations is also submitted,
-and the Secretary of State respectfully suggests, for the consideration
-of Congress, the propriety of limiting the power of ministers to make
-decrees and ulation, in the sense in which it is limited by paragraph
-431 of the article before named—that is, “to acts necessary to organize
+contain suggestions on the subject thereof. :
+A copy of Art XVI of the consist regulations so Submitted,
+and the Secretary of r i ly , for the consideration
+of ministers to make
+ion, in the sense in which it is limited by paragraph
+431 of the e be: fore named—that is, “ to acts necessary to organize
and give efficiency to the courts created by the act.”
-
-Respectfully submitted.
+Respectful submitted.
HAMILTON FISH.
-
-The PRESIDENT,
+The PRESIDENT.
List of accompanying papers.
1. Regulations for the consular courts of the United States in Japan.
-Mr. Fish to Mr. De Long, September 10, 1870.
+2. Mr. Fish to Mr. De Long, September 10, 1870,
\ No newline at end of file
diff --git a/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin b/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
index db2639a6..701b724f 100644
--- a/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
+++ b/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
@@ -9,151 +9,131 @@
-
-
-
- 41st Congress, }
+
+
+
+ 41st CONGRESS, } SENATE.
- 3d Session.
+ 3d Session.
-
-
- PRESIDENT OF THE UNITED STATES,
+
+
+ PRESIDENT OF THE UNITED STATES
-
- COMMUNICATING
+
+
+ A copy of regulations for the consular courts of the United States in Japan,
+
+ decreed and issued by the minister of the United States in that country.
-
- A copy of regulations for the consular courts of the United States in Japan,
+
+
+ Janvary 27, 1871—Read, referred to the Committee on Commerce, and ordered to be
- decreed and issued by the minister of the United States in that country.
+ printed,
-
- JaNvany 2, 1871.—Read, referred to the Committee on Commerce, and ordered to be
-
- printed.
-
-
-
-
- To the Senate and House of Representatives :
+
+
+ To the Senate and House of Representatives :
-
- I transmit herewith, for the consideration of Congress, a report from
+
+ I transmit herewith, for the consideration of Congress, a report from
- the Secretary of State, and the papers which accompanied it, concern-
+ the Secretary of State, and the papers which accompanied it, concern-
- ing regulations for the consular courts of the United States in Ja,
+ ing regulations for the consular courts of the United States in Ja
-
- U. 8. GRANT,
+
+ U. 8. GRAN
-
- WASHINGTON, January 27, 1871.
+
+ WASHINGTON, January 27, 1871.
-
- DEPARTMENT OF STATE,
+
+
+ DEPARTMENT OF STATE,
- Washington, January 26, 1870,
+ Washington, January 26, 1870.
-
-
-
- The Seeretary of State has the honor to submit herewith, for revision
+ The Secretary of State has the honor to submit herewith, for revision
- by Congress, in conformity with the provisions of section 6 of the act
+ by Congress, in conformity with the provisions of section 6 of the act
- approved 22d of June, 1860, a copy of “regulations for the consular
+ approved 22d of June, 1860, a copy of “regulations for the consular
- courts of the United States in Japan,” decreed and issued by C. E.
+ courts of the United States in Japan,” decreed and issued by C. E.
- De Long, the minister of the United States in that country, in Septem-
+ De Long, the minister of the United States in that country, in Septem-
- ber, 1870; and also the papers mentioned in the subjoined list, which
+ ber, 1870; and also the papers mentioned in the subjoined list, which
- contain suggestions on the subject thereof.
+ contain suggestions on the subject thereof. :
-
-
-
- A copy of Art XX-VI of the consular regulations is also submitted,
+ A copy of Art XVI of the consist regulations so Submitted,
- and the Secretary of State respectfully suggests, for the consideration
+ and the Secretary of r i ly , for the consideration
- of Congress, the propriety of limiting the power of ministers to make
+ of ministers to make
- decrees and ulation, in the sense in which it is limited by paragraph
+ ion, in the sense in which it is limited by paragraph
- 431 of the article before named—that is, “to acts necessary to organize
+ 431 of the e be: fore named—that is, “ to acts necessary to organize
- and give efficiency to the courts created by the act.”
+ and give efficiency to the courts created by the act.”
+
+ Respectful submitted.
+
+ HAMILTON FISH.
+
+ The PRESIDENT.
-
- Respectfully submitted.
-
- HAMILTON FISH.
+
+
+ List of accompanying papers.
-
- The PRESIDENT,
+
+
+ 1. Regulations for the consular courts of the United States in Japan.
+
+ 2. Mr. Fish to Mr. De Long, September 10, 1870,
-
- List of accompanying papers.
-
-
-
-
- 1. Regulations for the consular courts of the United States in Japan.
-
- Mr. Fish to Mr. De Long, September 10, 1870.
-
-
-
-
-
+
diff --git a/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/stderr.bin b/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/stderr.bin
index 55bff330..ef6539e7 100644
--- a/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/stderr.bin
+++ b/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/stderr.bin
@@ -1,3 +1,3 @@
Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
-OSD: Weak margin (2.72) for 1056 blob text block, but using orientation anyway: 0
-Detected 263 diacritics
+OSD: Weak margin (5.18) for 850 blob text block, but using orientation anyway: 0
+Detected 180 diacritics
diff --git a/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/txt.bin b/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/txt.bin
index bcfdcd9f..dc29a8a6 100644
--- a/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/txt.bin
+++ b/tests/cache/palette/__-l__eng__000001.ocr.png__000001__hocr__txt/txt.bin
@@ -1,57 +1,51 @@
-41st Congress, }
+41st CONGRESS, } SENATE.
3d Session.
MESSAGE
OF THE
-PRESIDENT OF THE UNITED STATES,
-
-COMMUNICATING
+PRESIDENT OF THE UNITED STATES
A copy of regulations for the consular courts of the United States in Japan,
decreed and issued by the minister of the United States in that country.
-JaNvany 2, 1871.—Read, referred to the Committee on Commerce, and ordered to be
-printed.
+Janvary 27, 1871—Read, referred to the Committee on Commerce, and ordered to be
+printed,
To the Senate and House of Representatives :
I transmit herewith, for the consideration of Congress, a report from
the Secretary of State, and the papers which accompanied it, concern-
-ing regulations for the consular courts of the United States in Ja,
+ing regulations for the consular courts of the United States in Ja
-U. 8. GRANT,
+U. 8. GRAN
WASHINGTON, January 27, 1871.
DEPARTMENT OF STATE,
-Washington, January 26, 1870,
-
-The Seeretary of State has the honor to submit herewith, for revision
+Washington, January 26, 1870.
+The Secretary of State has the honor to submit herewith, for revision
by Congress, in conformity with the provisions of section 6 of the act
approved 22d of June, 1860, a copy of “regulations for the consular
courts of the United States in Japan,” decreed and issued by C. E.
De Long, the minister of the United States in that country, in Septem-
ber, 1870; and also the papers mentioned in the subjoined list, which
-contain suggestions on the subject thereof.
-
-A copy of Art XX-VI of the consular regulations is also submitted,
-and the Secretary of State respectfully suggests, for the consideration
-of Congress, the propriety of limiting the power of ministers to make
-decrees and ulation, in the sense in which it is limited by paragraph
-431 of the article before named—that is, “to acts necessary to organize
+contain suggestions on the subject thereof. :
+A copy of Art XVI of the consist regulations so Submitted,
+and the Secretary of r i ly , for the consideration
+of ministers to make
+ion, in the sense in which it is limited by paragraph
+431 of the e be: fore named—that is, “ to acts necessary to organize
and give efficiency to the courts created by the act.”
-
-Respectfully submitted.
+Respectful submitted.
HAMILTON FISH.
-
-The PRESIDENT,
+The PRESIDENT.
List of accompanying papers.
1. Regulations for the consular courts of the United States in Japan.
-Mr. Fish to Mr. De Long, September 10, 1870.
+2. Mr. Fish to Mr. De Long, September 10, 1870,
\ No newline at end of file
diff --git a/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin b/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin
index 376a9238..5ae998aa 100644
Binary files a/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin and b/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin b/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
index b91fb22a..592383ef 100644
--- a/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
+++ b/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin
@@ -1,3 +1 @@
Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
-Warning. Invalid resolution 10 dpi. Using 70 instead.
-Estimating resolution as 328
diff --git a/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin b/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin
index 216dd092..1d83edbb 100644
--- a/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin
+++ b/tests/cache/poster/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin
@@ -2,7 +2,6 @@ The LinnSequencer
32 Track MIDI Sequence Recorder
The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
-
extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
© Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
@@ -54,7 +53,6 @@ Editing
To erase a wrong note, simply hold ERASE and press
the note to be erased just before it plays in the sequence—
when played back, it will be gone. Notes may also be
-
added, erased, or changed using the SINGLE STEP func-
tion. To overdub notes at specific points within a sequence,
diff --git a/tests/cache/skew/__-l__eng__--psm__7__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin b/tests/cache/skew/__-l__eng__--psm__7__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin
index aec1974b..bdfeaa1d 100644
Binary files a/tests/cache/skew/__-l__eng__--psm__7__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin and b/tests/cache/skew/__-l__eng__--psm__7__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/skew/__-l__eng__--psm__7__000001.ocr.png__000001__hocr__txt/hocr.bin b/tests/cache/skew/__-l__eng__--psm__7__000001.ocr.png__000001__hocr__txt/hocr.bin
index 07e2d206..020f1f18 100644
--- a/tests/cache/skew/__-l__eng__--psm__7__000001.ocr.png__000001__hocr__txt/hocr.bin
+++ b/tests/cache/skew/__-l__eng__--psm__7__000001.ocr.png__000001__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
+
The LinnSequencer
diff --git a/tests/cache/skew/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin b/tests/cache/skew/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin
index 19e67e82..a1cae482 100644
Binary files a/tests/cache/skew/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin and b/tests/cache/skew/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/pdf.bin differ
diff --git a/tests/cache/skew/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin b/tests/cache/skew/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
index 2a7d649f..593df43e 100644
--- a/tests/cache/skew/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
+++ b/tests/cache/skew/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-