diff --git a/tests/cache/2400dpi/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin b/tests/cache/2400dpi/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin new file mode 100644 index 00000000..5c249da3 --- /dev/null +++ b/tests/cache/2400dpi/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin @@ -0,0 +1,177 @@ + + + +
++ + i + a + la + Waterman + +
++ + 4 + ons + linzen + +
+ ++ + 3 + liter + water + +
+ ++ + 3 + uien + +
+ ++ + bloem, + boter + +
+ ++ + 2 + kopjes + melk + +
+ ++ + laurier, + kruidnagel, + kerrie, + zout + +
++ + De + linzgen + wassen + en + in-l + liter + kokend + wa- + + + ter + 1 + dag + laten + weken, + 2 + liter + water + bij + + + de + linzen + voegen, + zonder + het + water + waarin + + + ze + geweekt + zijn + af + te + gieten, + De + helft + van + + + de + uien + bakken + met + laurier + en + Kruidnagel. + + + Alle + uien, + kerrie + en + zgout + bij + de + linzen + + + voegen, + Alles + aan + de + kook + brengen, + Van + de + + + bloem + met + boter + en + melk + een + papje + maken + en + + + verder + afmaken + met + de + soep, + Als + de + linzen + + + gfgaar + Zijn + is + de + soep + klaar. + +
++ + Tarnose + +
++ + Bokale + oa + +
++ + Lehuntze + +
++ + Mugerre + +
++ + Milafranga + Komunikabideak + +
++ + BAIONA + zeiteninsiie + — + +
++ + 7 + Trenbideak + ----- + +
++ + t\ + Basusarri + — + spmeans:20141004 + ae: + . + _ + ~ + +
++ + Covfefe + is + a + perfectly + cromulent + word. + +
++ + Linzensoep + a + la + Waterman + +
++ + 4 + ons + linzen + +
+ ++ + 3 + liter + water + +
+ ++ + 3 + uien + +
+ ++ + bloem, + boter + +
+ ++ + 2 + kopjes + melk + +
+ ++ + laurier, + kruidnagel, + kerrie, + zout + +
++ + De + linzgen + wassen + en + in-l + liter + kokend + wa- + + + ter + 1 + dag + laten + weken, + 2 + liter + water + bij + + + de + linzen + voegen, + zonder + het + water + waarin + + + ze + geweekt + zijn + af + te + gieten, + De + helft + van + + + de + uien + bakken + met + laurier + en + Kruidnagel. + + + Alle + uien, + kerrie + en + zgout + bij + de + linzen + + + voegen, + Alles + aan + de + kook + brengen, + Van + de + + + bloem + met + boter + en + melk + een + papje + maken + en + + + verder + afmaken + met + de + soep, + Als + de + linzen + + + gfgaar + Zijn + is + de + soep + klaar. + +
+diff --git a/tests/cache/aspect/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin b/tests/cache/aspect/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin index b9dfc556..bc89ff94 100644 Binary files a/tests/cache/aspect/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin and b/tests/cache/aspect/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin differ diff --git a/tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin b/tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin index b0c5d5ce..ae8ef762 100644 --- a/tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin +++ b/tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin @@ -9,7 +9,7 @@
-
diff --git a/tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin b/tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin
index 173db9a3..f68abaf6 100644
Binary files a/tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin and b/tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin differ
diff --git a/tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/hocr.bin b/tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/hocr.bin
index 3df28d53..58eab038 100644
--- a/tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/hocr.bin
+++ b/tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
diff --git a/tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt/pdf.bin b/tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt/pdf.bin
index b22b5314..7048ee01 100644
Binary files a/tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt/pdf.bin and b/tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt/pdf.bin differ
diff --git a/tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin b/tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin
index b868be24..7c8fd82d 100644
--- a/tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin
+++ b/tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
diff --git a/tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt/pdf.bin b/tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt/pdf.bin
index f02a24f5..97934a26 100644
Binary files a/tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt/pdf.bin and b/tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt/pdf.bin differ
diff --git a/tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt/hocr.bin b/tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt/hocr.bin
index c7d84c09..dff5cf96 100644
--- a/tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt/hocr.bin
+++ b/tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
diff --git a/tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt/pdf.bin b/tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt/pdf.bin
index 5dffa64b..3e9f904e 100644
Binary files a/tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt/pdf.bin and b/tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt/pdf.bin differ
diff --git a/tests/cache/ccitt/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin b/tests/cache/ccitt/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin
index a3c4f48e..19f93857 100644
--- a/tests/cache/ccitt/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin
+++ b/tests/cache/ccitt/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
diff --git a/tests/cache/ccitt/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin b/tests/cache/ccitt/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin
index 4f9d0ced..ba6a2fd3 100644
Binary files a/tests/cache/ccitt/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin and b/tests/cache/ccitt/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin differ
diff --git a/tests/cache/francais/__-l__deu__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin b/tests/cache/francais/__-l__deu__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin
new file mode 100644
index 00000000..d678997c
--- /dev/null
+++ b/tests/cache/francais/__-l__deu__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin
@@ -0,0 +1,104 @@
+
+
+
+
+
+
+ Portez
+ ce
+ vieux
+ whisky
+ au
+ juge
+
+
+ blond
+ qui
+ fume
+ sur
+ son
+ Ile
+
+
+ interieure,
+ a
+ cöte
+ de
+ l'alcöve
+
+
+ ovoide,
+ oU
+ les
+ büches
+ se
+
+
+ consument
+ dans
+ l'ätre,
+ ce
+ qui
+
+
+ ui
+ permet
+ de
+ penser
+ &
+ la
+
+
+ caenogenese
+ de
+ |'etre
+ dont
+ il
+
+
+ est
+ question
+ dans
+ la
+ cause
+
+
+ ambigu&
+ entendue
+ a
+ MoY,
+ dans
+
+
+ un
+ capharnaüm
+ qui,
+ pense-t-il,
+
+
+ diminue
+ ca
+ et
+ la
+ la
+ qualit&
+ de
+ son
+
+
+ ceuvre.
+
+
+
+ 600
+
+
+ 500
+ .
+
+
+ 400
+ _
+ EB
+ fp
+ ys
+
+
+ 300
+ —f—
+ EN
+ /
+ ~/
+ Y
+
+
+ Tg
+ ANA
+ a3
+
+
+ 100
+ -
+ nee
+ -eemiae
+
+
+ 0-+—-*
+ a
+ ee
+ ee
+ ee
+ eee
+
+
+ S
+ @
+ s
+ >
+ oO
+ ©
+ ve
+ S
+ )
+ @
+ +
+ &
+ &
+ “A
+ 5
+ oo
+
+
+ Se
+ °
+ Ps
+ as
+ ge
+ eS
+ €
+ x
+ ro
+ NS
+ Po
+ e?
+ &
+ s
+ AS
+
+
+ a
+ a
+ ©
+ FF
+ SF
+ HY
+ HK
+ SK
+ BM
+ ee
+ sO
+
+
+ e
+ <
+ Na
+ ‘
+ :
+ >
+ cy
+ xs
+ eS
+ @
+ Ww
+ a)
+ Oo
+
+
+ ee
+ S&S
+ FF
+ SF
+ HK
+ S
+ e
+ ©
+ 4
+
+
+ ~
+ &
+ e
+
+
+ 3
+ x
+
+
+
+ —¢—Support
+
+
+
+ —H—
+ No
+ vote[note
+ 1]
+
+
+ ir
+ Oppose
+
+
+ —=—Net[note
+ 2]
+
+
+
+ re
+ Percentage
+ [note
+ 3]
+
+
diff --git a/tests/cache/jbig2/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin b/tests/cache/jbig2/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin
index d5c2d0c8..cb72730c 100644
Binary files a/tests/cache/jbig2/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin and b/tests/cache/jbig2/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/pdf.bin differ
diff --git a/tests/cache/lichtenstein/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin b/tests/cache/lichtenstein/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin
index 5d0c3478..87bdb5ea 100644
--- a/tests/cache/lichtenstein/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin
+++ b/tests/cache/lichtenstein/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin
@@ -9,7 +9,7 @@
-
-
- ee
- if
- /)
- J:
-
-
- (
- H}
- :
- cha
-
-
- iy
- ‘
- H
+
+
+ Chapter
+ i
-
- THEY
- TIP-TOED
- ALONG.
-
-
-
- N
-
-
-
- :
- chapter
- J
-
-
-
- E
- went
- tip-toeing
- along
- a
- path
- amongst
-
-
-
- the
- trees
- back
- towards
- the
- end
- of
- the
-
-
- widow’s
- garden,
- stooping
- down
- so
- as
-
-
- the
- branches
- wouldn’t
- scrape
- our
- heads.
-
-
- When
- we
- was
- passing
- by
- the
- kitchen
-
-
- I
- fell
- over
- a
- root
- and
- made
- a
- noise.
-
-
- We
- scrouched
- down
- and
- laid
- still.
-
-
- Miss
- Watson’s
- big
- nigger,
- named
-
-
- Jim,
- was
- setting
- in
- the
- kitchen
- door
- ;
-
-
- we
- could
- see
- him
- pretty
- clear,
- because
-
-
- there
- was
- a
- light
- behind
- him.
- He
-
-
- got
- up
- and
- stretched
- his
- neck
- out
-
-
- about
- a
- minute,
- listening.
- Then
- he
-
-
- says,
+
+
+ lad
-
- **
- Who
- dah?”
+
+
+ ‘
+ We
+ went
+ tip-toeing
+ along
+ a
+ path
+ amongst
-
-
- He
- listened
- some
- more;
- then
- he
+
+ the
+ trees
+ back
+ towards
+ the
+ end
+ of
+ the
-
- come
- tip-toeing
- down
- and-
- stood
-
-
- right
- between
- us;
- we
- could
- a
- touched
-
-
- him,
- nearly.
- Well,
- likely
- it
- was
- min-
-
-
- utes
- and
- minutes
- that
- there
- warn’t
- a
-
-
- sound,
- and
- we
- all
- there
- so
- close
-
-
- together.
- ‘There
- was
- a
- place
- on
- my
-
-
- ankle
- that
- got
- to
- itching;
- but
- I
+
+ widow’s
+ garden,
+ stooping
+ down
+ so
+ as
-
- dasn’t
- scratch
- it;
- and
- then
- my
- ear
- begun
- to
- itch;
- and
- next
- my
- back,
- right
- be-
+
+
+
+ the
+ branches
+ wouldn’t
+ scrape
+ our
+ heads.
-
- tween
- my
- shoulders.
- Seemed
- like
- I’d
- die
- if
- I
- couldn’t
- scratch.
- Well,
- I’ve
+
+ When
+ we
+ was
+ passing
+ by
+ the
+ kitchen
-
- noticed
- that
- thing
- plenty
- of
- times
- since.
- If
- you
- are
- with
- the
- quality,
- or
- at
- a
+
+ I
+ fell
+ over
+ a
+ root
+ and
+ made
+ a
+ noise.
-
- funeral,
- or
- trying
- to
- go
- to
- sleep
- when
- you
- ain’t
- sleepy—if
- you
- are
- anywheres
+
+ We
+ scrouched
+ down
+ and
+ laid
+ still.
+
+
+ Miss
+ Watson’s
+ big
+ nigger,
+ named
+
+
+ Jim,
+ was
+ setting
+ in
+ the
+ kitchen
+ door;
+
+
+ we
+ could
+ see
+ him
+ pretty
+ clear,
+ because
+
+
+ there
+ was
+ a
+ light
+ behind
+ him.
+ He
+
+
+ got
+ up
+ and
+ stretched
+ his
+ neck
+ out
+
+
+ about
+ a
+ minute,
+ listening.
+ Then
+ he
+
+
+ says,
+
+
+
+ «Who
+ dah?”
+
+
+
+ He
+ listened
+ some
+ more;
+ then
+ he
+
+
+ come
+ tip-toeing
+ down
+ and.
+ stood
+
+
+ right
+ between
+ us;
+ we
+ could
+ a
+ touched
+
+
+ him,
+ nearly.
+ Well,
+ likely
+ it
+ was
+ min-
+
+
+ utes
+ and
+ minutes
+ that
+ there
+ warn’t
+ a
+
+
+ sound,
+ and
+ we
+ all
+ there
+ so
+ close
+
+
+ together.
+ ‘There
+ was
+ a
+ place
+ on
+ my
+
+
+ ankle
+ that
+ got
+ to
+ itching;
+ but
+ I
+
+
+ dasn’t
+ scratch
+ it;
+ and
+ then
+ my
+ ear
+ begun
+ to
+ itch;
+ and
+ next
+ my
+ back,
+ right
+ be-
+
+
+ tween
+ my
+ shoulders.
+ Seemed
+ like
+ I’d
+ die
+ if
+ I
+ couldn’t
+ scratch.
+ Well,
+ I’ve
+
+
+ noticed
+ that
+ thing
+ plenty
+ of
+ times
+ since.
+ If
+ you
+ are
+ with
+ the
+ quality,
+ or
+ at
+ a
+
+
+ funeral,
+ or
+ trying
+ to
+ go
+ to
+ sleep
+ when
+ you
+ ain’t
+ sleepy—if
+ you
+ are
+ anywheres
+
+
+
+ ‘qumY
+ TIP-TOED
+ ALONG.
diff --git a/tests/cache/multipage/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin b/tests/cache/multipage/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin
index 50dfc4c8..d77c385d 100644
--- a/tests/cache/multipage/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin
+++ b/tests/cache/multipage/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin
@@ -9,51 +9,59 @@
-
-
- —¢—Support
+
+
+ —
+ —esupport
-
-
- ==
- No
- vote[note
- 1]
-
-
- ie
- Oppose
-
-
- ——Net[note
- 2]
-
-
-
- =e
- Percentage
- [note
- 3]
+
+ 300
+
+ BE
+ No
+ votefnote
+ 1]
+
+
+
+ —
+
+
+ ay
+ >
+ Net[note
+ 2]
+
+
+
+ Percentage
+ [note
+ 3]
+
+