summaryrefslogtreecommitdiff
path: root/src/main/resources
diff options
context:
space:
mode:
authorAlisaLinUwU <alisalinuwu@gmail.com>2025-01-26 11:44:59 +0500
committerAlisaLinUwU <alisalinuwu@gmail.com>2025-01-26 11:44:59 +0500
commit7b8c476700f995c81a43ec46a14efdb42ea11b32 (patch)
tree3667f55209aa0dc50b46342b336f71ddc7aac883 /src/main/resources
Initializemain
Diffstat (limited to 'src/main/resources')
-rw-r--r--src/main/resources/META-INF/MANIFEST.MF3
-rw-r--r--src/main/resources/application.properties3
-rw-r--r--src/main/resources/templates/index.html172
-rw-r--r--src/main/resources/tessdata/configs/alto1
-rw-r--r--src/main/resources/tessdata/configs/ambigs.train7
-rw-r--r--src/main/resources/tessdata/configs/api_config1
-rw-r--r--src/main/resources/tessdata/configs/bigram5
-rw-r--r--src/main/resources/tessdata/configs/box.train12
-rw-r--r--src/main/resources/tessdata/configs/box.train.stderr13
-rw-r--r--src/main/resources/tessdata/configs/digits1
-rw-r--r--src/main/resources/tessdata/configs/get.images1
-rw-r--r--src/main/resources/tessdata/configs/hocr2
-rw-r--r--src/main/resources/tessdata/configs/inter2
-rw-r--r--src/main/resources/tessdata/configs/kannada4
-rw-r--r--src/main/resources/tessdata/configs/linebox2
-rw-r--r--src/main/resources/tessdata/configs/logfile1
-rw-r--r--src/main/resources/tessdata/configs/lstm.train11
-rw-r--r--src/main/resources/tessdata/configs/lstmbox1
-rw-r--r--src/main/resources/tessdata/configs/lstmdebug4
-rw-r--r--src/main/resources/tessdata/configs/makebox1
-rw-r--r--src/main/resources/tessdata/configs/page3
-rw-r--r--src/main/resources/tessdata/configs/pdf1
-rw-r--r--src/main/resources/tessdata/configs/quiet1
-rw-r--r--src/main/resources/tessdata/configs/rebox2
-rw-r--r--src/main/resources/tessdata/configs/strokewidth12
-rw-r--r--src/main/resources/tessdata/configs/tsv1
-rw-r--r--src/main/resources/tessdata/configs/txt3
-rw-r--r--src/main/resources/tessdata/configs/unlv2
-rw-r--r--src/main/resources/tessdata/configs/wordstrbox1
-rw-r--r--src/main/resources/tessdata/eng.traineddatabin0 -> 23466654 bytes
-rw-r--r--src/main/resources/tessdata/osd.traineddatabin0 -> 10562874 bytes
-rw-r--r--src/main/resources/tessdata/pdf.ttfbin0 -> 572 bytes
-rw-r--r--src/main/resources/tessdata/rus.traineddatabin0 -> 19920885 bytes
-rw-r--r--src/main/resources/tessdata/tessconfigs/batch1
-rw-r--r--src/main/resources/tessdata/tessconfigs/batch.nochop2
-rw-r--r--src/main/resources/tessdata/tessconfigs/matdemo7
-rw-r--r--src/main/resources/tessdata/tessconfigs/msdemo12
-rw-r--r--src/main/resources/tessdata/tessconfigs/nobatch1
-rw-r--r--src/main/resources/tessdata/tessconfigs/segdemo9
-rw-r--r--src/main/resources/tessdata/uzb.traineddatabin0 -> 10757098 bytes
-rw-r--r--src/main/resources/tessdata/uzb_cyrl.traineddatabin0 -> 4905658 bytes
41 files changed, 305 insertions, 0 deletions
diff --git a/src/main/resources/META-INF/MANIFEST.MF b/src/main/resources/META-INF/MANIFEST.MF
new file mode 100644
index 0000000..b9ceb2b
--- /dev/null
+++ b/src/main/resources/META-INF/MANIFEST.MF
@@ -0,0 +1,3 @@
+Manifest-Version: 1.0
+Main-Class: info.selflearner.ocr.OcrApplication
+
diff --git a/src/main/resources/application.properties b/src/main/resources/application.properties
new file mode 100644
index 0000000..6e2fc3b
--- /dev/null
+++ b/src/main/resources/application.properties
@@ -0,0 +1,3 @@
+spring.application.name=ocr
+spring.servlet.multipart.max-file-size=50MB
+spring.servlet.multipart.max-request-size=50MB
diff --git a/src/main/resources/templates/index.html b/src/main/resources/templates/index.html
new file mode 100644
index 0000000..9d63f8b
--- /dev/null
+++ b/src/main/resources/templates/index.html
@@ -0,0 +1,172 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="UTF-8">
+ <title>OCR</title>
+ <style>
+ button { display: none}
+
+ #passport:checked ~ #rus {
+ display: none;
+ }
+ </style>
+ <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.3/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-QWTKZyjpPEjISv5WaRU9OFeRpok6YctnYmDr5pNlyT2bRjXh0JMhjY6hW+ALEwIH" crossorigin="anonymous">
+ <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.3/dist/js/bootstrap.bundle.min.js" integrity="sha384-YvpcrYf0tY3lHB60NNkmXc5s9fDVZLESaAA55NDzOxhy9GkcIdslK1eN7N6jIeHz" crossorigin="anonymous"></script>
+</head>
+<body>
+ <div class="container col-xl-12 col-xxl-8 px-4 py-5">
+ <div class="form-group mx-sm-3 mb-2 p-md-5 border rounded-3 bg-body-tertiary" th:each="passport, iStat: ${passports}">
+ <div class="form-group row mb-2" th:if="${passport.subtype}">
+ <label th:for="passportSubType + ${iStat.index}" class="col-sm-2 col-form-label">Pasport turi:</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportSubtype + ${iStat.index}" th:id="passportSubtype + ${iStat.index}" th:value="|${passport.subtype}|" th:onclick="'copyToClipboard(\'passportSubtype' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[0]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ <div class="form-group row mb-2">
+ <label th:for="passportIssuer + ${iStat.index}" class="col-sm-2 col-form-label">Bergan davlat/firma:</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportIssuer + ${iStat.index}" th:id="passportIssuer + ${iStat.index}" th:value="|${passport.issuer}|" th:onclick="'copyToClipboard(\'passportIssuer' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[0]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ <div class="form-group row mb-2">
+ <label th:for="passportSurname + ${iStat.index}" class="col-sm-2 col-form-label">Familiyasi:</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportSurname + ${iStat.index}" th:id="passportSurname + ${iStat.index}" th:value="|${passport.surname}|" th:onclick="'copyToClipboard(\'passportSurname' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[0]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ <div class="form-group row mb-2">
+ <label th:for="passportGivenNames + ${iStat.index}" class="col-sm-2 col-form-label">Ismi(-lari):</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportGivenNames + ${iStat.index}" th:id="passportGivenNames + ${iStat.index}" th:value="|${passport.givenNames}|" th:onclick="'copyToClipboard(\'passportGivenNames' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[0]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ <div class="form-group row mb-2">
+ <label th:for="passportNumber + ${iStat.index}" class="col-sm-2 col-form-label">Pasport raqami:</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportNumber + ${iStat.index}" th:id="passportNumber + ${iStat.index}" th:value="|${passport.number}|" th:onclick="'copyToClipboard(\'passportNumber' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[1]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ <div class="form-group row mb-2">
+ <label th:for="passportNationality + ${iStat.index}" class="col-sm-2 col-form-label">Fuqaroligi:</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportNationality + ${iStat.index}" th:id="passportNationality + ${iStat.index}" th:value="|${passport.nationality}|" th:onclick="'copyToClipboard(\'passportNationality' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[1]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ <div class="form-group row mb-2">
+ <label th:for="passportDateOfBirth + ${iStat.index}" class="col-sm-2 col-form-label">Tug'ilgan sanasi:</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportDateOfBirth + ${iStat.index}" th:id="passportDateOfBirth + ${iStat.index}" th:value="|${#temporals.format(passport.dateOfBirth, 'dd.MM.yyyy')}|" th:onclick="'copyToClipboard(\'passportDateOfBirth' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[1]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ <div class="form-group row mb-2">
+ <label th:for="passportSex + ${iStat.index}" class="col-sm-2 col-form-label">Jinsi:</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportSex + ${iStat.index}" th:id="passportSex + ${iStat.index}" th:value="|${passport.sex}|" th:onclick="'copyToClipboard(\'passportSex' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[1]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ <div class="form-group row mb-2">
+ <label th:for="passportExpirationDate + ${iStat.index}" class="col-sm-2 col-form-label">Amal qilish muddati:</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportExpirationDate + ${iStat.index}" th:id="passportExpirationDate + ${iStat.index}" th:value="|${#temporals.format(passport.expirationDate, 'dd.MM.yyyy')}|" th:onclick="'copyToClipboard(\'passportExpirationDate' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[1]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ <div class="form-group row mb-3">
+ <label th:for="passportPersonalNumber + ${iStat.index}" class="col-sm-2 col-form-label">JSHSHIR:</label>
+ <div class="col-sm-9">
+ <input type="text" class="form-control" th:name="passportPersonalNumber + ${iStat.index}" th:id="passportPersonalNumber + ${iStat.index}" th:value="|${passport.personalNumber}|" th:onclick="'copyToClipboard(\'passportPersonalNumber' + ${iStat.index} + '\')'" readonly>
+ </div>
+ <div class="col-sm-1 text-center my-auto" th:text="|(${passport.mrzLinesConfidence[1]}%)|" data-toggle="tooltip" data-placement="top" title="Ishonchlilik darajasi"></div>
+ </div>
+ </div>
+ <a th:href="@{|/api/passport/excel?filename=Dokumentlar.xlsx|}" th:download="|Dokumentlar.xlsx|" th:if="${passports}">
+ <button class="btn btn-lg btn-success mx-sm-3" type="submit">Excel</button>
+ </a>
+ <div class="col-lg-12 text-lg-start" th:each="ocr, iStat: ${ocrs}">
+ <textarea class="form-control mt-3 fs-4 p-4 p-md-5 border rounded-3 bg-body-tertiary" th:name="text + ${iStat.index}" th:id="text + ${iStat.index}" rows="10" th:text="|${ocr}|" readonly></textarea>
+ <button class="mt-2 w-20 btn btn-lg btn-secondary" th:onclick="'copyToClipboard(\'text' + ${iStat.index} + '\')'">Nusxa olish</button>
+ </div>
+ <div class="col-md-10 mx-auto col-lg-5 mt-5">
+ <form class="p-4 p-md-5 border rounded-3 bg-body-tertiary" action="/api/files" method="post" enctype="multipart/form-data">
+ <div class="form-floating mb-3">
+ <input type="file" class="form-control" id="files" name="files" multiple>
+ <label for="files">Fayllar</label>
+ </div>
+ <p>Tilni(-larni) tanlang:</p>
+ <div class="form-check form-check-inline mb-3">
+ <input class="form-check-input" type="checkbox" id="eng" name="eng" value="eng" checked>
+ <label class="form-check-label" for="eng">Ingliz</label>
+ </div>
+ <div class="form-check form-check-inline mb-3">
+ <input class="form-check-input" type="checkbox" id="rus" name="rus" value="rus" checked>
+ <label class="form-check-label" for="rus">Rus</label>
+ </div>
+ <div class="form-check form-check-inline mb-3">
+ <input class="form-check-input" type="checkbox" id="uzb" name="uzb" value="uzb" checked>
+ <label class="form-check-label" for="uzb">Uzbek</label>
+ </div>
+ <div class="form-check form-check-inline mb-3">
+ <input class="form-check-input" type="checkbox" id="uzb_cyrl" name="uzb_cyrl" value="uzb_cyrl" checked>
+ <label class="form-check-label" for="uzb_cyrl">Uzbek (kirilcha)</label>
+ </div>
+ <p>Dokumen turini tanlang:</p>
+ <div class="form-check form-check-inline mb-3">
+ <input class="form-check-input" type="radio" id="other" name="documentType" value="other" onclick="enableAllLanguages()" checked>
+ <label class="form-check-label" for="other">Boshqa</label>
+ </div>
+ <div class="form-check form-check-inline mb-3">
+ <input class="form-check-input" type="radio" id="passport" name="documentType" value="passport" onclick="disableAllLanguages()">
+ <label class="form-check-label" for="passport">Pasport</label>
+ </div>
+ <button class="w-100 btn btn-lg btn-primary" type="submit">Yuborish</button>
+ </form>
+ </div>
+ </div>
+ <script>
+ function copyToClipboard(id) {
+ var text = document.getElementById(id);
+
+ text.select();
+ text.setSelectionRange(0, 99999); // For mobile devices
+
+ navigator.clipboard.writeText(text.value);
+
+ alert("Nusxa olindi!");
+ }
+
+ function disableAllLanguages() {
+ document.getElementById("eng").disabled = true;
+ document.getElementById("rus").disabled = true;
+ document.getElementById("uzb").disabled = true;
+ document.getElementById("uzb_cyrl").disabled = true;
+ }
+
+ function enableAllLanguages() {
+ document.getElementById("eng").disabled = false;
+ document.getElementById("rus").disabled = false;
+ document.getElementById("uzb").disabled = false;
+ document.getElementById("uzb_cyrl").disabled = false;
+ }
+
+ if (document.getElementById('other').checked) {
+ document.getElementById("eng").disabled = false;
+ document.getElementById("rus").disabled = false;
+ document.getElementById("uzb").disabled = false;
+ document.getElementById("uzb_cyrl").disabled = false;
+ } else if (document.getElementById('passport').checked) {
+ document.getElementById("eng").disabled = true;
+ document.getElementById("rus").disabled = true;
+ document.getElementById("uzb").disabled = true;
+ document.getElementById("uzb_cyrl").disabled = true;
+ }
+ </script>
+</body>
+</html> \ No newline at end of file
diff --git a/src/main/resources/tessdata/configs/alto b/src/main/resources/tessdata/configs/alto
new file mode 100644
index 0000000..0dd12a7
--- /dev/null
+++ b/src/main/resources/tessdata/configs/alto
@@ -0,0 +1 @@
+tessedit_create_alto 1
diff --git a/src/main/resources/tessdata/configs/ambigs.train b/src/main/resources/tessdata/configs/ambigs.train
new file mode 100644
index 0000000..23035a1
--- /dev/null
+++ b/src/main/resources/tessdata/configs/ambigs.train
@@ -0,0 +1,7 @@
+tessedit_ambigs_training 1
+load_freq_dawg 0
+load_punc_dawg 0
+load_system_dawg 0
+load_number_dawg 0
+ambigs_debug_level 3
+load_fixed_length_dawgs 0
diff --git a/src/main/resources/tessdata/configs/api_config b/src/main/resources/tessdata/configs/api_config
new file mode 100644
index 0000000..5cd6ec0
--- /dev/null
+++ b/src/main/resources/tessdata/configs/api_config
@@ -0,0 +1 @@
+tessedit_zero_rejection T
diff --git a/src/main/resources/tessdata/configs/bigram b/src/main/resources/tessdata/configs/bigram
new file mode 100644
index 0000000..5d6c2d0
--- /dev/null
+++ b/src/main/resources/tessdata/configs/bigram
@@ -0,0 +1,5 @@
+load_bigram_dawg True
+tessedit_enable_bigram_correction True
+tessedit_bigram_debug 3
+save_raw_choices True
+save_alt_choices True
diff --git a/src/main/resources/tessdata/configs/box.train b/src/main/resources/tessdata/configs/box.train
new file mode 100644
index 0000000..d39f268
--- /dev/null
+++ b/src/main/resources/tessdata/configs/box.train
@@ -0,0 +1,12 @@
+disable_character_fragments T
+file_type .bl
+textord_fast_pitch_test T
+tessedit_zero_rejection T
+tessedit_minimal_rejection F
+tessedit_write_rep_codes F
+edges_children_fix F
+edges_childarea 0.65
+edges_boxarea 0.9
+tessedit_resegment_from_boxes T
+tessedit_train_from_boxes T
+textord_no_rejects T
diff --git a/src/main/resources/tessdata/configs/box.train.stderr b/src/main/resources/tessdata/configs/box.train.stderr
new file mode 100644
index 0000000..82754e9
--- /dev/null
+++ b/src/main/resources/tessdata/configs/box.train.stderr
@@ -0,0 +1,13 @@
+file_type .bl
+#tessedit_use_nn F
+textord_fast_pitch_test T
+tessedit_zero_rejection T
+tessedit_minimal_rejection F
+tessedit_write_rep_codes F
+edges_children_fix F
+edges_childarea 0.65
+edges_boxarea 0.9
+tessedit_resegment_from_boxes T
+tessedit_train_from_boxes T
+#textord_repeat_extraction F
+textord_no_rejects T
diff --git a/src/main/resources/tessdata/configs/digits b/src/main/resources/tessdata/configs/digits
new file mode 100644
index 0000000..6a329f8
--- /dev/null
+++ b/src/main/resources/tessdata/configs/digits
@@ -0,0 +1 @@
+tessedit_char_whitelist 0123456789-.
diff --git a/src/main/resources/tessdata/configs/get.images b/src/main/resources/tessdata/configs/get.images
new file mode 100644
index 0000000..7d00b61
--- /dev/null
+++ b/src/main/resources/tessdata/configs/get.images
@@ -0,0 +1 @@
+tessedit_write_images T
diff --git a/src/main/resources/tessdata/configs/hocr b/src/main/resources/tessdata/configs/hocr
new file mode 100644
index 0000000..5ab372e
--- /dev/null
+++ b/src/main/resources/tessdata/configs/hocr
@@ -0,0 +1,2 @@
+tessedit_create_hocr 1
+hocr_font_info 0
diff --git a/src/main/resources/tessdata/configs/inter b/src/main/resources/tessdata/configs/inter
new file mode 100644
index 0000000..252f1a1
--- /dev/null
+++ b/src/main/resources/tessdata/configs/inter
@@ -0,0 +1,2 @@
+interactive_display_mode T
+tessedit_display_outwords T
diff --git a/src/main/resources/tessdata/configs/kannada b/src/main/resources/tessdata/configs/kannada
new file mode 100644
index 0000000..c6ac105
--- /dev/null
+++ b/src/main/resources/tessdata/configs/kannada
@@ -0,0 +1,4 @@
+textord_skewsmooth_offset 8
+textord_skewsmooth_offset2 8
+textord_merge_desc 0.5
+textord_no_rejects 1
diff --git a/src/main/resources/tessdata/configs/linebox b/src/main/resources/tessdata/configs/linebox
new file mode 100644
index 0000000..bd9c114
--- /dev/null
+++ b/src/main/resources/tessdata/configs/linebox
@@ -0,0 +1,2 @@
+tessedit_resegment_from_line_boxes 1
+tessedit_make_boxes_from_boxes 1
diff --git a/src/main/resources/tessdata/configs/logfile b/src/main/resources/tessdata/configs/logfile
new file mode 100644
index 0000000..a160f9b
--- /dev/null
+++ b/src/main/resources/tessdata/configs/logfile
@@ -0,0 +1 @@
+debug_file tesseract.log
diff --git a/src/main/resources/tessdata/configs/lstm.train b/src/main/resources/tessdata/configs/lstm.train
new file mode 100644
index 0000000..5ff3772
--- /dev/null
+++ b/src/main/resources/tessdata/configs/lstm.train
@@ -0,0 +1,11 @@
+file_type .bl
+textord_fast_pitch_test T
+tessedit_zero_rejection T
+tessedit_minimal_rejection F
+tessedit_write_rep_codes F
+edges_children_fix F
+edges_childarea 0.65
+edges_boxarea 0.9
+tessedit_train_line_recognizer T
+textord_no_rejects T
+tessedit_init_config_only T
diff --git a/src/main/resources/tessdata/configs/lstmbox b/src/main/resources/tessdata/configs/lstmbox
new file mode 100644
index 0000000..a6f2ced
--- /dev/null
+++ b/src/main/resources/tessdata/configs/lstmbox
@@ -0,0 +1 @@
+tessedit_create_lstmbox 1
diff --git a/src/main/resources/tessdata/configs/lstmdebug b/src/main/resources/tessdata/configs/lstmdebug
new file mode 100644
index 0000000..3fa3dee
--- /dev/null
+++ b/src/main/resources/tessdata/configs/lstmdebug
@@ -0,0 +1,4 @@
+stopper_debug_level 1
+classify_debug_level 1
+segsearch_debug_level 1
+language_model_debug_level 3
diff --git a/src/main/resources/tessdata/configs/makebox b/src/main/resources/tessdata/configs/makebox
new file mode 100644
index 0000000..3d90ac2
--- /dev/null
+++ b/src/main/resources/tessdata/configs/makebox
@@ -0,0 +1 @@
+tessedit_create_boxfile 1
diff --git a/src/main/resources/tessdata/configs/page b/src/main/resources/tessdata/configs/page
new file mode 100644
index 0000000..9928884
--- /dev/null
+++ b/src/main/resources/tessdata/configs/page
@@ -0,0 +1,3 @@
+tessedit_create_page_xml 1
+# page_xml_polygon 1
+# page_xml_level 0
diff --git a/src/main/resources/tessdata/configs/pdf b/src/main/resources/tessdata/configs/pdf
new file mode 100644
index 0000000..59645d7
--- /dev/null
+++ b/src/main/resources/tessdata/configs/pdf
@@ -0,0 +1 @@
+tessedit_create_pdf 1
diff --git a/src/main/resources/tessdata/configs/quiet b/src/main/resources/tessdata/configs/quiet
new file mode 100644
index 0000000..35b59a9
--- /dev/null
+++ b/src/main/resources/tessdata/configs/quiet
@@ -0,0 +1 @@
+debug_file /dev/null
diff --git a/src/main/resources/tessdata/configs/rebox b/src/main/resources/tessdata/configs/rebox
new file mode 100644
index 0000000..f8342b4
--- /dev/null
+++ b/src/main/resources/tessdata/configs/rebox
@@ -0,0 +1,2 @@
+tessedit_resegment_from_boxes 1
+tessedit_make_boxes_from_boxes 1
diff --git a/src/main/resources/tessdata/configs/strokewidth b/src/main/resources/tessdata/configs/strokewidth
new file mode 100644
index 0000000..e95b592
--- /dev/null
+++ b/src/main/resources/tessdata/configs/strokewidth
@@ -0,0 +1,12 @@
+textord_show_blobs 0
+textord_debug_tabfind 3
+textord_tabfind_show_partitions 1
+textord_tabfind_show_initial_partitions 1
+textord_tabfind_show_columns 1
+textord_tabfind_show_blocks 1
+textord_tabfind_show_initialtabs 1
+textord_tabfind_show_finaltabs 1
+textord_tabfind_show_strokewidths 1
+textord_tabfind_show_vlines 0
+textord_tabfind_show_images 1
+tessedit_dump_pageseg_images 0
diff --git a/src/main/resources/tessdata/configs/tsv b/src/main/resources/tessdata/configs/tsv
new file mode 100644
index 0000000..dc52478
--- /dev/null
+++ b/src/main/resources/tessdata/configs/tsv
@@ -0,0 +1 @@
+tessedit_create_tsv 1
diff --git a/src/main/resources/tessdata/configs/txt b/src/main/resources/tessdata/configs/txt
new file mode 100644
index 0000000..a0cc952
--- /dev/null
+++ b/src/main/resources/tessdata/configs/txt
@@ -0,0 +1,3 @@
+# This config file should be used with other config files which create renderers.
+# usage example: tesseract eurotext.tif eurotext txt hocr pdf
+tessedit_create_txt 1
diff --git a/src/main/resources/tessdata/configs/unlv b/src/main/resources/tessdata/configs/unlv
new file mode 100644
index 0000000..d2e22f5
--- /dev/null
+++ b/src/main/resources/tessdata/configs/unlv
@@ -0,0 +1,2 @@
+tessedit_write_unlv 1
+unlv_tilde_crunching T
diff --git a/src/main/resources/tessdata/configs/wordstrbox b/src/main/resources/tessdata/configs/wordstrbox
new file mode 100644
index 0000000..38cd41c
--- /dev/null
+++ b/src/main/resources/tessdata/configs/wordstrbox
@@ -0,0 +1 @@
+tessedit_create_wordstrbox 1
diff --git a/src/main/resources/tessdata/eng.traineddata b/src/main/resources/tessdata/eng.traineddata
new file mode 100644
index 0000000..f4744c2
--- /dev/null
+++ b/src/main/resources/tessdata/eng.traineddata
Binary files differ
diff --git a/src/main/resources/tessdata/osd.traineddata b/src/main/resources/tessdata/osd.traineddata
new file mode 100644
index 0000000..183644a
--- /dev/null
+++ b/src/main/resources/tessdata/osd.traineddata
Binary files differ
diff --git a/src/main/resources/tessdata/pdf.ttf b/src/main/resources/tessdata/pdf.ttf
new file mode 100644
index 0000000..d1472b2
--- /dev/null
+++ b/src/main/resources/tessdata/pdf.ttf
Binary files differ
diff --git a/src/main/resources/tessdata/rus.traineddata b/src/main/resources/tessdata/rus.traineddata
new file mode 100644
index 0000000..8b71c2d
--- /dev/null
+++ b/src/main/resources/tessdata/rus.traineddata
Binary files differ
diff --git a/src/main/resources/tessdata/tessconfigs/batch b/src/main/resources/tessdata/tessconfigs/batch
new file mode 100644
index 0000000..a681e4a
--- /dev/null
+++ b/src/main/resources/tessdata/tessconfigs/batch
@@ -0,0 +1 @@
+# No content needed as all defaults are correct.
diff --git a/src/main/resources/tessdata/tessconfigs/batch.nochop b/src/main/resources/tessdata/tessconfigs/batch.nochop
new file mode 100644
index 0000000..ebaab94
--- /dev/null
+++ b/src/main/resources/tessdata/tessconfigs/batch.nochop
@@ -0,0 +1,2 @@
+chop_enable 0
+wordrec_enable_assoc 0
diff --git a/src/main/resources/tessdata/tessconfigs/matdemo b/src/main/resources/tessdata/tessconfigs/matdemo
new file mode 100644
index 0000000..c34567b
--- /dev/null
+++ b/src/main/resources/tessdata/tessconfigs/matdemo
@@ -0,0 +1,7 @@
+#################################################
+# Adaptive Matcher Using PreAdapted Templates
+#################################################
+
+classify_enable_adaptive_debugger 1
+matcher_debug_flags 6
+matcher_debug_level 1
diff --git a/src/main/resources/tessdata/tessconfigs/msdemo b/src/main/resources/tessdata/tessconfigs/msdemo
new file mode 100644
index 0000000..9c1184a
--- /dev/null
+++ b/src/main/resources/tessdata/tessconfigs/msdemo
@@ -0,0 +1,12 @@
+#################################################
+# Adaptive Matcher Using PreAdapted Templates
+#################################################
+
+classify_enable_adaptive_debugger 1
+matcher_debug_flags 6
+matcher_debug_level 1
+
+wordrec_display_splits 0
+wordrec_display_all_blobs 1
+wordrec_display_segmentations 2
+classify_debug_level 1
diff --git a/src/main/resources/tessdata/tessconfigs/nobatch b/src/main/resources/tessdata/tessconfigs/nobatch
new file mode 100644
index 0000000..8b13789
--- /dev/null
+++ b/src/main/resources/tessdata/tessconfigs/nobatch
@@ -0,0 +1 @@
+
diff --git a/src/main/resources/tessdata/tessconfigs/segdemo b/src/main/resources/tessdata/tessconfigs/segdemo
new file mode 100644
index 0000000..eaff69f
--- /dev/null
+++ b/src/main/resources/tessdata/tessconfigs/segdemo
@@ -0,0 +1,9 @@
+#################################################
+# Adaptive Matcher Using PreAdapted Templates
+#################################################
+
+wordrec_display_splits 0
+wordrec_display_all_blobs 1
+wordrec_display_segmentations 2
+classify_debug_level 1
+stopper_debug_level 1
diff --git a/src/main/resources/tessdata/uzb.traineddata b/src/main/resources/tessdata/uzb.traineddata
new file mode 100644
index 0000000..cf9f7e0
--- /dev/null
+++ b/src/main/resources/tessdata/uzb.traineddata
Binary files differ
diff --git a/src/main/resources/tessdata/uzb_cyrl.traineddata b/src/main/resources/tessdata/uzb_cyrl.traineddata
new file mode 100644
index 0000000..434d277
--- /dev/null
+++ b/src/main/resources/tessdata/uzb_cyrl.traineddata
Binary files differ