Upload folder using huggingface_hub

.env

@@ -0,0 +1,4 @@
+RAPIDAPI_KEY=5a696b0394msh0cd412236e3a960p1e9b93jsn024e50e3cf38
+OPENAI_API_KEY=sk-proj-HuKZeBLHxlovlNrXz0sYT3BlbkFJOUvgR40paSXuxrgQFice
+IMGBB_API_KEY=81b9cf806504b27cb58b457d211e21df
+

.gitattributes

@@ -33,3 +33,32 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ocr-application/bin/python filter=lfs diff=lfs merge=lfs -text
+ocr-application/bin/python3 filter=lfs diff=lfs merge=lfs -text
+ocr-application/bin/python3.1 filter=lfs diff=lfs merge=lfs -text
+ocr-application/bin/python3.11 filter=lfs diff=lfs merge=lfs -text
+ocr-application/bin/ruff filter=lfs diff=lfs merge=lfs -text
+ocr-application/bin/sqlite3 filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/libcrypto.3.dylib filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/libcrypto.a filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/libcrypto.dylib filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/libpython3.11.dylib filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/libsqlite3.0.dylib filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/libsqlite3.dylib filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/libtcl8.6.dylib filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/libtk8.6.dylib filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/ensurepip/_bundled/pip-24.0-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/ensurepip/_bundled/setuptools-65.5.0-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/lib-dynload/unicodedata.cpython-311-darwin.so filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/PIL/.dylibs/libfreetype.6.dylib filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/PIL/.dylibs/libharfbuzz.0.dylib filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/gradio/frpc_darwin_arm64_v0.2 filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/numpy/_core/_multiarray_umath.cpython-311-darwin.so filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/pandas/_libs/algos.cpython-311-darwin.so filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/pandas/_libs/groupby.cpython-311-darwin.so filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/pandas/_libs/hashtable.cpython-311-darwin.so filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/pandas/_libs/interval.cpython-311-darwin.so filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/pandas/_libs/join.cpython-311-darwin.so filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/pydantic_core/_pydantic_core.cpython-311-darwin.so filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/python3.11/site-packages/uvloop/loop.cpython-311-darwin.so filter=lfs diff=lfs merge=lfs -text
+ocr-application/lib/sqlite3.44.2/libsqlite3.44.2.dylib filter=lfs diff=lfs merge=lfs -text

.github/workflows/update_space.yml

@@ -0,0 +1,28 @@
+name: Run Python script
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.9'
+
+    - name: Install Gradio
+      run: python -m pip install gradio
+
+    - name: Log in to Hugging Face
+      run: python -c 'import huggingface_hub; huggingface_hub.login(token="${{ secrets.hf_token }}")'
+
+    - name: Deploy to Spaces
+      run: gradio deploy

README.md

@@ -1,12 +1,6 @@
 ---
-title: Ocr Text Processing
-emoji: 🏃
-colorFrom: green
-colorTo: indigo
+title: ocr-text-processing
+app_file: app.py
 sdk: gradio
 sdk_version: 4.39.0
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,112 @@
+import gradio as gr
+import http.client
+import json
+import requests
+import base64
+import os
+from dotenv import load_dotenv
+from openai import OpenAI
+
+# Load environment variables
+load_dotenv()
+
+# Function to upload image to imgbb
+def upload_image_to_imgbb(image_path):
+    try:
+        with open(image_path, "rb") as file:
+            url = "https://api.imgbb.com/1/upload"
+            payload = {
+                "key": os.getenv("IMGBB_API_KEY"),
+                "image": base64.b64encode(file.read()).decode()
+            }
+            res = requests.post(url, data=payload)
+            res.raise_for_status()  # Raises an HTTPError for bad responses
+            return res.json()['data']['url']
+    except Exception as e:
+        return f"Error uploading image: {str(e)}"
+
+# OCR API request
+def get_ocr_results(image_url):
+    try:
+        conn = http.client.HTTPSConnection("ocr43.p.rapidapi.com")
+        payload = f"-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"url\"\r\n\r\n{image_url}\r\n-----011000010111000001101001--\r\n\r\n"
+        headers = {
+            'x-rapidapi-key': os.getenv("RAPIDAPI_KEY"),
+            'x-rapidapi-host': "ocr43.p.rapidapi.com",
+            'Content-Type': "multipart/form-data; boundary=---011000010111000001101001"
+        }
+        conn.request("POST", "/v1/results", payload, headers)
+        res = conn.getresponse()
+        data = res.read()
+        return data.decode("utf-8")
+    except Exception as e:
+        return f"Error in OCR processing: {str(e)}"
+
+# OpenAI API configuration
+openai_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
+# Function to process OCR results with OpenAI
+def process_ocr_with_gpt(ocr_results):
+    try:
+        prompt = f"""
+        You are an AI assistant tasked with processing OCR results and providing a clean, formatted output.
+        Here are the OCR results:
+
+        {ocr_results}
+
+        Please process this information and provide a clean, well-formatted output. If there are any obvious errors in the OCR, please correct them. Format the output in a clear and readable manner.
+        """
+
+        response = openai_client.chat.completions.create(
+            model="gpt-3.5-turbo",
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant that processes OCR results."},
+                {"role": "user", "content": prompt}
+            ]
+        )
+
+        return response.choices[0].message.content
+    except Exception as e:
+        return f"Error in GPT processing: {str(e)}"
+
+# Gradio interface function
+def process_image(image):
+    try:
+        # Save the image temporarily and get its path
+        image_path = "temp_image.png"
+        image.save(image_path)
+        
+        # Upload image to imgbb and get URL
+        image_url = upload_image_to_imgbb(image_path)
+        if image_url.startswith("Error"):
+            return image_url, "Failed to process due to image upload error"
+        
+        # Get OCR results
+        ocr_results = get_ocr_results(image_url)
+        if ocr_results.startswith("Error"):
+            return ocr_results, "Failed to process due to OCR error"
+        
+        # Process with GPT
+        processed_results = process_ocr_with_gpt(ocr_results)
+        
+        # Clean up temporary file
+        os.remove(image_path)
+        
+        return ocr_results, processed_results
+    except Exception as e:
+        return f"Error in image processing: {str(e)}", "Failed to process due to an error"
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=process_image,
+    inputs=gr.Image(type="pil"),
+    outputs=[
+        gr.Textbox(label="OCR Results"),
+        gr.Textbox(label="Processed Results")
+    ],
+    title="OCR and Text Processing App",
+    description="Upload an image to extract text and process it."
+)
+
+# Launch the app
+iface.launch()

ocr-application/bin/2to3

@@ -0,0 +1,5 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python3.11
+import sys
+from lib2to3.main import main
+
+sys.exit(main("lib2to3.fixes"))

ocr-application/bin/2to3-3.11

@@ -0,0 +1,5 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python3.11
+import sys
+from lib2to3.main import main
+
+sys.exit(main("lib2to3.fixes"))

ocr-application/bin/bzcmp

@@ -0,0 +1,76 @@
+#!/bin/sh
+# sh is buggy on RS/6000 AIX 3.2. Replace above line with #!/bin/ksh
+
+# Bzcmp/diff wrapped for bzip2, 
+# adapted from zdiff by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
+
+# Bzcmp and bzdiff are used to invoke the cmp or the  diff  pro-
+# gram  on compressed files.  All options specified are passed
+# directly to cmp or diff.  If only 1 file is specified,  then
+# the  files  compared  are file1 and an uncompressed file1.gz.
+# If two files are specified, then they are  uncompressed  (if
+# necessary) and fed to cmp or diff.  The exit status from cmp
+# or diff is preserved.
+
+PATH="/usr/bin:/bin:$PATH"; export PATH
+prog=`echo $0 | sed 's|.*/||'`
+case "$prog" in
+  *cmp) comp=${CMP-cmp}   ;;
+  *)    comp=${DIFF-diff} ;;
+esac
+
+OPTIONS=
+FILES=
+for ARG
+do
+    case "$ARG" in
+    -*)	OPTIONS="$OPTIONS $ARG";;
+     *)	if test -f "$ARG"; then
+            FILES="$FILES $ARG"
+        else
+            echo "${prog}: $ARG not found or not a regular file"
+	    exit 1
+        fi ;;
+    esac
+done
+if test -z "$FILES"; then
+	echo "Usage: $prog [${comp}_options] file [file]"
+	exit 1
+fi
+set $FILES
+if test $# -eq 1; then
+	FILE=`echo "$1" | sed 's/.bz2$//'`
+	bzip2 -cd "$FILE.bz2" | $comp $OPTIONS - "$FILE"
+	STAT="$?"
+
+elif test $# -eq 2; then
+	case "$1" in
+        *.bz2)
+                case "$2" in
+	        *.bz2)
+			F=`echo "$2" | sed 's|.*/||;s|.bz2$||'`
+			tmp=`mktemp "${TMPDIR:-/tmp}"/bzdiff.XXXXXXXXXX` || {
+			      echo 'cannot create a temporary file' >&2
+			      exit 1
+			}
+                        bzip2 -cdfq "$2" > "$tmp"
+                        bzip2 -cdfq "$1" | $comp $OPTIONS - "$tmp"
+                        STAT="$?"
+			/bin/rm -f "$tmp";;
+
+                *)      bzip2 -cdfq "$1" | $comp $OPTIONS - "$2"
+                        STAT="$?";;
+                esac;;
+        *)      case "$2" in
+	        *.bz2)
+                        bzip2 -cdfq "$2" | $comp $OPTIONS "$1" -
+                        STAT="$?";;
+                *)      $comp $OPTIONS "$1" "$2"
+                        STAT="$?";;
+                esac;;
+	esac
+else
+	echo "Usage: $prog [${comp}_options] file [file]"
+	exit 1
+fi
+exit "$STAT"

ocr-application/bin/bzdiff

@@ -0,0 +1,76 @@
+#!/bin/sh
+# sh is buggy on RS/6000 AIX 3.2. Replace above line with #!/bin/ksh
+
+# Bzcmp/diff wrapped for bzip2, 
+# adapted from zdiff by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
+
+# Bzcmp and bzdiff are used to invoke the cmp or the  diff  pro-
+# gram  on compressed files.  All options specified are passed
+# directly to cmp or diff.  If only 1 file is specified,  then
+# the  files  compared  are file1 and an uncompressed file1.gz.
+# If two files are specified, then they are  uncompressed  (if
+# necessary) and fed to cmp or diff.  The exit status from cmp
+# or diff is preserved.
+
+PATH="/usr/bin:/bin:$PATH"; export PATH
+prog=`echo $0 | sed 's|.*/||'`
+case "$prog" in
+  *cmp) comp=${CMP-cmp}   ;;
+  *)    comp=${DIFF-diff} ;;
+esac
+
+OPTIONS=
+FILES=
+for ARG
+do
+    case "$ARG" in
+    -*)	OPTIONS="$OPTIONS $ARG";;
+     *)	if test -f "$ARG"; then
+            FILES="$FILES $ARG"
+        else
+            echo "${prog}: $ARG not found or not a regular file"
+	    exit 1
+        fi ;;
+    esac
+done
+if test -z "$FILES"; then
+	echo "Usage: $prog [${comp}_options] file [file]"
+	exit 1
+fi
+set $FILES
+if test $# -eq 1; then
+	FILE=`echo "$1" | sed 's/.bz2$//'`
+	bzip2 -cd "$FILE.bz2" | $comp $OPTIONS - "$FILE"
+	STAT="$?"
+
+elif test $# -eq 2; then
+	case "$1" in
+        *.bz2)
+                case "$2" in
+	        *.bz2)
+			F=`echo "$2" | sed 's|.*/||;s|.bz2$||'`
+			tmp=`mktemp "${TMPDIR:-/tmp}"/bzdiff.XXXXXXXXXX` || {
+			      echo 'cannot create a temporary file' >&2
+			      exit 1
+			}
+                        bzip2 -cdfq "$2" > "$tmp"
+                        bzip2 -cdfq "$1" | $comp $OPTIONS - "$tmp"
+                        STAT="$?"
+			/bin/rm -f "$tmp";;
+
+                *)      bzip2 -cdfq "$1" | $comp $OPTIONS - "$2"
+                        STAT="$?";;
+                esac;;
+        *)      case "$2" in
+	        *.bz2)
+                        bzip2 -cdfq "$2" | $comp $OPTIONS "$1" -
+                        STAT="$?";;
+                *)      $comp $OPTIONS "$1" "$2"
+                        STAT="$?";;
+                esac;;
+	esac
+else
+	echo "Usage: $prog [${comp}_options] file [file]"
+	exit 1
+fi
+exit "$STAT"

ocr-application/bin/bzegrep

@@ -0,0 +1,85 @@
+#!/bin/sh
+
+# Bzgrep wrapped for bzip2, 
+# adapted from zgrep by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
+## zgrep notice:
+## zgrep -- a wrapper around a grep program that decompresses files as needed
+## Adapted from a version sent by Charles Levert <charles@comm.polymtl.ca>
+
+PATH="/usr/bin:$PATH"; export PATH
+
+prog=`echo $0 | sed 's|.*/||'`
+case "$prog" in
+	*egrep)	grep=${EGREP-egrep}	;;
+	*fgrep)	grep=${FGREP-fgrep}	;;
+	*)	grep=${GREP-grep}	;;
+esac
+pat=""
+while test $# -ne 0; do
+  case "$1" in
+  -e | -f) opt="$opt $1"; shift; pat="$1"
+           if test "$grep" = grep; then  # grep is buggy with -e on SVR4
+             grep=egrep
+           fi;;
+  -A | -B) opt="$opt $1 $2"; shift;;
+  -*)	   opt="$opt $1";;
+   *)      if test -z "$pat"; then
+	     pat="$1"
+	   else
+	     break;
+           fi;;
+  esac
+  shift
+done
+
+if test -z "$pat"; then
+  echo "grep through bzip2 files"
+  echo "usage: $prog [grep_options] pattern [files]"
+  exit 1
+fi
+
+list=0
+silent=0
+op=`echo "$opt" | sed -e 's/ //g' -e 's/-//g'`
+case "$op" in
+  *l*) list=1
+esac
+case "$op" in
+  *h*) silent=1
+esac
+
+if test $# -eq 0; then
+  bzip2 -cdfq | $grep $opt "$pat"
+  exit $?
+fi
+
+res=0
+for i do
+  if test -f "$i"; then :; else if test -f "$i.bz2"; then i="$i.bz2"; fi; fi
+  if test $list -eq 1; then
+    bzip2 -cdfq "$i" | $grep $opt "$pat" 2>&1 > /dev/null && echo $i
+    r=$?
+  elif test $# -eq 1 -o $silent -eq 1; then
+    bzip2 -cdfq "$i" | $grep $opt "$pat"
+    r=$?
+  else
+    j=$(echo "$i" | sed 's/\\/&&/g;s/|/\\&/g;s/&/\\&/g')
+    j=`printf "%s" "$j" | tr '\n' ' '`
+    # A trick adapted from
+    # https://groups.google.com/forum/#!original/comp.unix.shell/x1345iu10eg/Nn1n-1r1uU0J
+    # that has the same effect as the following bash code:
+    # bzip2 -cdfq "$i" | $grep $opt "$pat" | sed "s|^|${j}:|"
+    # r=${PIPESTATUS[1]}
+    exec 3>&1
+    eval `
+      exec 4>&1 >&3 3>&-
+      {
+        bzip2 -cdfq "$i" 4>&-
+      } | {
+        $grep $opt "$pat" 4>&-; echo "r=$?;" >&4
+      } | sed "s|^|${j}:|"
+    `
+  fi
+  test "$r" -ne 0 && res="$r"
+done
+exit $res

ocr-application/bin/bzfgrep

@@ -0,0 +1,85 @@
+#!/bin/sh
+
+# Bzgrep wrapped for bzip2, 
+# adapted from zgrep by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
+## zgrep notice:
+## zgrep -- a wrapper around a grep program that decompresses files as needed
+## Adapted from a version sent by Charles Levert <charles@comm.polymtl.ca>
+
+PATH="/usr/bin:$PATH"; export PATH
+
+prog=`echo $0 | sed 's|.*/||'`
+case "$prog" in
+	*egrep)	grep=${EGREP-egrep}	;;
+	*fgrep)	grep=${FGREP-fgrep}	;;
+	*)	grep=${GREP-grep}	;;
+esac
+pat=""
+while test $# -ne 0; do
+  case "$1" in
+  -e | -f) opt="$opt $1"; shift; pat="$1"
+           if test "$grep" = grep; then  # grep is buggy with -e on SVR4
+             grep=egrep
+           fi;;
+  -A | -B) opt="$opt $1 $2"; shift;;
+  -*)	   opt="$opt $1";;
+   *)      if test -z "$pat"; then
+	     pat="$1"
+	   else
+	     break;
+           fi;;
+  esac
+  shift
+done
+
+if test -z "$pat"; then
+  echo "grep through bzip2 files"
+  echo "usage: $prog [grep_options] pattern [files]"
+  exit 1
+fi
+
+list=0
+silent=0
+op=`echo "$opt" | sed -e 's/ //g' -e 's/-//g'`
+case "$op" in
+  *l*) list=1
+esac
+case "$op" in
+  *h*) silent=1
+esac
+
+if test $# -eq 0; then
+  bzip2 -cdfq | $grep $opt "$pat"
+  exit $?
+fi
+
+res=0
+for i do
+  if test -f "$i"; then :; else if test -f "$i.bz2"; then i="$i.bz2"; fi; fi
+  if test $list -eq 1; then
+    bzip2 -cdfq "$i" | $grep $opt "$pat" 2>&1 > /dev/null && echo $i
+    r=$?
+  elif test $# -eq 1 -o $silent -eq 1; then
+    bzip2 -cdfq "$i" | $grep $opt "$pat"
+    r=$?
+  else
+    j=$(echo "$i" | sed 's/\\/&&/g;s/|/\\&/g;s/&/\\&/g')
+    j=`printf "%s" "$j" | tr '\n' ' '`
+    # A trick adapted from
+    # https://groups.google.com/forum/#!original/comp.unix.shell/x1345iu10eg/Nn1n-1r1uU0J
+    # that has the same effect as the following bash code:
+    # bzip2 -cdfq "$i" | $grep $opt "$pat" | sed "s|^|${j}:|"
+    # r=${PIPESTATUS[1]}
+    exec 3>&1
+    eval `
+      exec 4>&1 >&3 3>&-
+      {
+        bzip2 -cdfq "$i" 4>&-
+      } | {
+        $grep $opt "$pat" 4>&-; echo "r=$?;" >&4
+      } | sed "s|^|${j}:|"
+    `
+  fi
+  test "$r" -ne 0 && res="$r"
+done
+exit $res

ocr-application/bin/bzgrep

@@ -0,0 +1,85 @@
+#!/bin/sh
+
+# Bzgrep wrapped for bzip2, 
+# adapted from zgrep by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
+## zgrep notice:
+## zgrep -- a wrapper around a grep program that decompresses files as needed
+## Adapted from a version sent by Charles Levert <charles@comm.polymtl.ca>
+
+PATH="/usr/bin:$PATH"; export PATH
+
+prog=`echo $0 | sed 's|.*/||'`
+case "$prog" in
+	*egrep)	grep=${EGREP-egrep}	;;
+	*fgrep)	grep=${FGREP-fgrep}	;;
+	*)	grep=${GREP-grep}	;;
+esac
+pat=""
+while test $# -ne 0; do
+  case "$1" in
+  -e | -f) opt="$opt $1"; shift; pat="$1"
+           if test "$grep" = grep; then  # grep is buggy with -e on SVR4
+             grep=egrep
+           fi;;
+  -A | -B) opt="$opt $1 $2"; shift;;
+  -*)	   opt="$opt $1";;
+   *)      if test -z "$pat"; then
+	     pat="$1"
+	   else
+	     break;
+           fi;;
+  esac
+  shift
+done
+
+if test -z "$pat"; then
+  echo "grep through bzip2 files"
+  echo "usage: $prog [grep_options] pattern [files]"
+  exit 1
+fi
+
+list=0
+silent=0
+op=`echo "$opt" | sed -e 's/ //g' -e 's/-//g'`
+case "$op" in
+  *l*) list=1
+esac
+case "$op" in
+  *h*) silent=1
+esac
+
+if test $# -eq 0; then
+  bzip2 -cdfq | $grep $opt "$pat"
+  exit $?
+fi
+
+res=0
+for i do
+  if test -f "$i"; then :; else if test -f "$i.bz2"; then i="$i.bz2"; fi; fi
+  if test $list -eq 1; then
+    bzip2 -cdfq "$i" | $grep $opt "$pat" 2>&1 > /dev/null && echo $i
+    r=$?
+  elif test $# -eq 1 -o $silent -eq 1; then
+    bzip2 -cdfq "$i" | $grep $opt "$pat"
+    r=$?
+  else
+    j=$(echo "$i" | sed 's/\\/&&/g;s/|/\\&/g;s/&/\\&/g')
+    j=`printf "%s" "$j" | tr '\n' ' '`
+    # A trick adapted from
+    # https://groups.google.com/forum/#!original/comp.unix.shell/x1345iu10eg/Nn1n-1r1uU0J
+    # that has the same effect as the following bash code:
+    # bzip2 -cdfq "$i" | $grep $opt "$pat" | sed "s|^|${j}:|"
+    # r=${PIPESTATUS[1]}
+    exec 3>&1
+    eval `
+      exec 4>&1 >&3 3>&-
+      {
+        bzip2 -cdfq "$i" 4>&-
+      } | {
+        $grep $opt "$pat" 4>&-; echo "r=$?;" >&4
+      } | sed "s|^|${j}:|"
+    `
+  fi
+  test "$r" -ne 0 && res="$r"
+done
+exit $res

ocr-application/bin/bzless

@@ -0,0 +1,61 @@
+#!/bin/sh
+
+# Bzmore wrapped for bzip2, 
+# adapted from zmore by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
+
+PATH="/usr/bin:$PATH"; export PATH
+
+prog=`echo $0 | sed 's|.*/||'`
+case "$prog" in
+	*less)	more=less	;;
+	*)	more=more       ;;
+esac
+
+if test "`echo -n a`" = "-n a"; then
+  # looks like a SysV system:
+  n1=''; n2='\c'
+else
+  n1='-n'; n2=''
+fi
+oldtty=`stty -g 2>/dev/null`
+if stty -cbreak 2>/dev/null; then
+  cb='cbreak'; ncb='-cbreak'
+else
+  # 'stty min 1' resets eof to ^a on both SunOS and SysV!
+  cb='min 1 -icanon'; ncb='icanon eof ^d'
+fi
+if test $? -eq 0 -a -n "$oldtty"; then
+   trap 'stty $oldtty 2>/dev/null; exit' 0 2 3 5 10 13 15
+else
+   trap 'stty $ncb echo 2>/dev/null; exit' 0 2 3 5 10 13 15
+fi
+
+if test $# = 0; then
+    if test -t 0; then
+	echo usage: $prog files...
+    else
+	bzip2 -cdfq | eval $more
+    fi
+else
+    FIRST=1
+    for FILE
+    do
+	if test $FIRST -eq 0; then
+		echo $n1 "--More--(Next file: $FILE)$n2"
+		stty $cb -echo 2>/dev/null
+		ANS=`dd bs=1 count=1 2>/dev/null` 
+		stty $ncb echo 2>/dev/null
+		echo " "
+		if test "$ANS" = 'e' -o "$ANS" = 'q'; then
+			exit
+		fi
+	fi
+	if test "$ANS" != 's'; then
+		echo "------> $FILE <------"
+		bzip2 -cdfq "$FILE" | eval $more
+	fi
+	if test -t; then
+		FIRST=0
+	fi
+    done
+fi

ocr-application/bin/bzmore

@@ -0,0 +1,61 @@
+#!/bin/sh
+
+# Bzmore wrapped for bzip2, 
+# adapted from zmore by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
+
+PATH="/usr/bin:$PATH"; export PATH
+
+prog=`echo $0 | sed 's|.*/||'`
+case "$prog" in
+	*less)	more=less	;;
+	*)	more=more       ;;
+esac
+
+if test "`echo -n a`" = "-n a"; then
+  # looks like a SysV system:
+  n1=''; n2='\c'
+else
+  n1='-n'; n2=''
+fi
+oldtty=`stty -g 2>/dev/null`
+if stty -cbreak 2>/dev/null; then
+  cb='cbreak'; ncb='-cbreak'
+else
+  # 'stty min 1' resets eof to ^a on both SunOS and SysV!
+  cb='min 1 -icanon'; ncb='icanon eof ^d'
+fi
+if test $? -eq 0 -a -n "$oldtty"; then
+   trap 'stty $oldtty 2>/dev/null; exit' 0 2 3 5 10 13 15
+else
+   trap 'stty $ncb echo 2>/dev/null; exit' 0 2 3 5 10 13 15
+fi
+
+if test $# = 0; then
+    if test -t 0; then
+	echo usage: $prog files...
+    else
+	bzip2 -cdfq | eval $more
+    fi
+else
+    FIRST=1
+    for FILE
+    do
+	if test $FIRST -eq 0; then
+		echo $n1 "--More--(Next file: $FILE)$n2"
+		stty $cb -echo 2>/dev/null
+		ANS=`dd bs=1 count=1 2>/dev/null` 
+		stty $ncb echo 2>/dev/null
+		echo " "
+		if test "$ANS" = 'e' -o "$ANS" = 'q'; then
+			exit
+		fi
+	fi
+	if test "$ANS" != 's'; then
+		echo "------> $FILE <------"
+		bzip2 -cdfq "$FILE" | eval $more
+	fi
+	if test -t; then
+		FIRST=0
+	fi
+    done
+fi

ocr-application/bin/c_rehash

@@ -0,0 +1,252 @@
+#!/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_0b9u2d318b/croot/openssl_1718384848925/_build_env/bin/perl
+
+# WARNING: do not edit!
+# Generated by Makefile from tools/c_rehash.in
+# Copyright 1999-2022 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the Apache License 2.0 (the "License").  You may not use
+# this file except in compliance with the License.  You can obtain a copy
+# in the file LICENSE in the source distribution or at
+# https://www.openssl.org/source/license.html
+
+# Perl c_rehash script, scan all files in a directory
+# and add symbolic links to their hash values.
+
+my $dir = "";
+my $prefix = "/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application";
+
+my $errorcount = 0;
+my $openssl = $ENV{OPENSSL} || "openssl";
+my $pwd;
+my $x509hash = "-subject_hash";
+my $crlhash = "-hash";
+my $verbose = 0;
+my $symlink_exists=eval {symlink("",""); 1};
+my $removelinks = 1;
+
+##  Parse flags.
+while ( $ARGV[0] =~ /^-/ ) {
+    my $flag = shift @ARGV;
+    last if ( $flag eq '--');
+    if ( $flag eq '-old') {
+        $x509hash = "-subject_hash_old";
+        $crlhash = "-hash_old";
+    } elsif ( $flag eq '-h' || $flag eq '-help' ) {
+        help();
+    } elsif ( $flag eq '-n' ) {
+        $removelinks = 0;
+    } elsif ( $flag eq '-v' ) {
+        $verbose++;
+    }
+    else {
+        print STDERR "Usage error; try -h.\n";
+        exit 1;
+    }
+}
+
+sub help {
+    print "Usage: c_rehash [-old] [-h] [-help] [-v] [dirs...]\n";
+    print "   -old use old-style digest\n";
+    print "   -h or -help print this help text\n";
+    print "   -v print files removed and linked\n";
+    exit 0;
+}
+
+eval "require Cwd";
+if (defined(&Cwd::getcwd)) {
+    $pwd=Cwd::getcwd();
+} else {
+    $pwd=`pwd`;
+    chomp($pwd);
+}
+
+# DOS/Win32 or Unix delimiter?  Prefix our installdir, then search.
+my $path_delim = ($pwd =~ /^[a-z]\:/i) ? ';' : ':';
+$ENV{PATH} = "$prefix/bin" . ($ENV{PATH} ? $path_delim . $ENV{PATH} : "");
+
+if (! -x $openssl) {
+    my $found = 0;
+    foreach (split /$path_delim/, $ENV{PATH}) {
+        if (-x "$_/$openssl") {
+            $found = 1;
+            $openssl = "$_/$openssl";
+            last;
+        }
+    }
+    if ($found == 0) {
+        print STDERR "c_rehash: rehashing skipped ('openssl' program not available)\n";
+        exit 0;
+    }
+}
+
+if (@ARGV) {
+    @dirlist = @ARGV;
+} elsif ($ENV{SSL_CERT_DIR}) {
+    @dirlist = split /$path_delim/, $ENV{SSL_CERT_DIR};
+} else {
+    $dirlist[0] = "$dir/certs";
+}
+
+if (-d $dirlist[0]) {
+    chdir $dirlist[0];
+    $openssl="$pwd/$openssl" if (!-x $openssl);
+    chdir $pwd;
+}
+
+foreach (@dirlist) {
+    if (-d $_ ) {
+        if ( -w $_) {
+            hash_dir($_);
+        } else {
+            print "Skipping $_, can't write\n";
+            $errorcount++;
+        }
+    }
+}
+exit($errorcount);
+
+sub copy_file {
+    my ($src_fname, $dst_fname) = @_;
+
+    if (open(my $in, "<", $src_fname)) {
+        if (open(my $out, ">", $dst_fname)) {
+            print $out $_ while (<$in>);
+            close $out;
+        } else {
+            warn "Cannot open $dst_fname for write, $!";
+        }
+        close $in;
+    } else {
+        warn "Cannot open $src_fname for read, $!";
+    }
+}
+
+sub hash_dir {
+    my $dir = shift;
+    my %hashlist;
+
+    print "Doing $dir\n";
+
+    if (!chdir $dir) {
+        print STDERR "WARNING: Cannot chdir to '$dir', $!\n";
+        return;
+    }
+
+    opendir(DIR, ".") || print STDERR "WARNING: Cannot opendir '.', $!\n";
+    my @flist = sort readdir(DIR);
+    closedir DIR;
+    if ( $removelinks ) {
+        # Delete any existing symbolic links
+        foreach (grep {/^[\da-f]+\.r{0,1}\d+$/} @flist) {
+            if (-l $_) {
+                print "unlink $_\n" if $verbose;
+                unlink $_ || warn "Can't unlink $_, $!\n";
+            }
+        }
+    }
+    FILE: foreach $fname (grep {/\.(pem)|(crt)|(cer)|(crl)$/} @flist) {
+        # Check to see if certificates and/or CRLs present.
+        my ($cert, $crl) = check_file($fname);
+        if (!$cert && !$crl) {
+            print STDERR "WARNING: $fname does not contain a certificate or CRL: skipping\n";
+            next;
+        }
+        link_hash_cert($fname) if ($cert);
+        link_hash_crl($fname) if ($crl);
+    }
+
+    chdir $pwd;
+}
+
+sub check_file {
+    my ($is_cert, $is_crl) = (0,0);
+    my $fname = $_[0];
+
+    open(my $in, "<", $fname);
+    while(<$in>) {
+        if (/^-----BEGIN (.*)-----/) {
+            my $hdr = $1;
+            if ($hdr =~ /^(X509 |TRUSTED |)CERTIFICATE$/) {
+                $is_cert = 1;
+                last if ($is_crl);
+            } elsif ($hdr eq "X509 CRL") {
+                $is_crl = 1;
+                last if ($is_cert);
+            }
+        }
+    }
+    close $in;
+    return ($is_cert, $is_crl);
+}
+
+sub compute_hash {
+    my $fh;
+    if ( $^O eq "VMS" ) {
+        # VMS uses the open through shell
+        # The file names are safe there and list form is unsupported
+        if (!open($fh, "-|", join(' ', @_))) {
+            print STDERR "Cannot compute hash on '$fname'\n";
+            return;
+        }
+    } else {
+        if (!open($fh, "-|", @_)) {
+            print STDERR "Cannot compute hash on '$fname'\n";
+            return;
+        }
+    }
+    return (<$fh>, <$fh>);
+}
+
+# Link a certificate to its subject name hash value, each hash is of
+# the form <hash>.<n> where n is an integer. If the hash value already exists
+# then we need to up the value of n, unless its a duplicate in which
+# case we skip the link. We check for duplicates by comparing the
+# certificate fingerprints
+
+sub link_hash_cert {
+    link_hash($_[0], 'cert');
+}
+
+# Same as above except for a CRL. CRL links are of the form <hash>.r<n>
+
+sub link_hash_crl {
+    link_hash($_[0], 'crl');
+}
+
+sub link_hash {
+    my ($fname, $type) = @_;
+    my $is_cert = $type eq 'cert';
+
+    my ($hash, $fprint) = compute_hash($openssl,
+                                       $is_cert ? "x509" : "crl",
+                                       $is_cert ? $x509hash : $crlhash,
+                                       "-fingerprint", "-noout",
+                                       "-in", $fname);
+    chomp $hash;
+    $hash =~ s/^.*=// if !$is_cert;
+    chomp $fprint;
+    return if !$hash;
+    $fprint =~ s/^.*=//;
+    $fprint =~ tr/://d;
+    my $suffix = 0;
+    # Search for an unused hash filename
+    my $crlmark = $is_cert ? "" : "r";
+    while(exists $hashlist{"$hash.$crlmark$suffix"}) {
+        # Hash matches: if fingerprint matches its a duplicate cert
+        if ($hashlist{"$hash.$crlmark$suffix"} eq $fprint) {
+            my $what = $is_cert ? 'certificate' : 'CRL';
+            print STDERR "WARNING: Skipping duplicate $what $fname\n";
+            return;
+        }
+        $suffix++;
+    }
+    $hash .= ".$crlmark$suffix";
+    if ($symlink_exists) {
+        print "link $fname -> $hash\n" if $verbose;
+        symlink $fname, $hash || warn "Can't symlink, $!";
+    } else {
+        print "copy $fname -> $hash\n" if $verbose;
+        copy_file($fname, $hash);
+    }
+    $hashlist{$hash} = $fprint;
+}

ocr-application/bin/distro

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from distro.distro import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

ocr-application/bin/dotenv

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from dotenv.__main__ import cli
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli())

ocr-application/bin/email_validator

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from email_validator.__main__ import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

ocr-application/bin/f2py

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from numpy.f2py.f2py2e import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

ocr-application/bin/fastapi

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from fastapi_cli.cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

ocr-application/bin/fonttools

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from fontTools.__main__ import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

ocr-application/bin/gradio

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from gradio.cli import cli
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli())

ocr-application/bin/httpx

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from httpx import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

ocr-application/bin/huggingface-cli

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from huggingface_hub.commands.huggingface_cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

ocr-application/bin/idle3

@@ -0,0 +1,5 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python3.11
+
+from idlelib.pyshell import main
+if __name__ == '__main__':
+    main()

ocr-application/bin/idle3.11

@@ -0,0 +1,5 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python3.11
+
+from idlelib.pyshell import main
+if __name__ == '__main__':
+    main()

ocr-application/bin/lzcmp

@@ -0,0 +1,215 @@
+#!/bin/sh
+
+# Copyright (C) 1998, 2002, 2006, 2007 Free Software Foundation
+# Copyright (C) 1993 Jean-loup Gailly
+
+# Modified for XZ Utils by Andrew Dudman and Lasse Collin.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT. With gzip, bzip2, and lzop it's OK to just unset the
+# environment variables.
+xz='xz --format=auto'
+unset GZIP BZIP BZIP2 LZOP
+
+case ${0##*/} in
+  *cmp*) prog=xzcmp; cmp=${CMP:-cmp};;
+  *)     prog=xzdiff; cmp=${DIFF:-diff};;
+esac
+
+version="$prog (XZ Utils) 5.4.6"
+
+usage="Usage: ${0##*/} [OPTION]... FILE1 [FILE2]
+Compare FILE1 to FILE2, using their uncompressed contents if they are
+compressed.  If FILE2 is omitted, then the files compared are FILE1 and
+FILE1 from which the compression format suffix has been stripped.
+
+Do comparisons like '$cmp' does.  OPTIONs are the same as for '$cmp'.
+
+Report bugs to <xz@tukaani.org>."
+
+# sed script to escape all ' for the shell, and then (to handle trailing
+# newlines correctly) turn trailing X on last line into '.
+escape='
+  s/'\''/'\''\\'\'''\''/g
+  $s/X$/'\''/
+'
+
+while :; do
+  case $1 in
+    --h*) printf '%s\n' "$usage" || exit 2; exit;;
+    --v*) printf '%s\n' "$version" || exit 2; exit;;
+    --) shift; break;;
+    -*\'*) cmp="$cmp '"`printf '%sX\n' "$1" | sed "$escape"`;;
+    -?*) cmp="$cmp '$1'";;
+    *) break;;
+  esac
+  shift
+done
+cmp="$cmp --"
+
+for file; do
+  test "X$file" = X- || <"$file" || exit 2
+done
+
+# xz needs -qQ to ignore warnings like unsupported check type.
+xz1="$xz -qQ"
+xz2="$xz -qQ"
+xz_status=0
+exec 3>&1
+
+if test $# -eq 1; then
+  case $1 in
+    *[-.]xz | *[-.]lzma | *[-.]lz | *.t[lx]z)
+      ;;
+    *[-.]bz2 | *.tbz | *.tbz2)
+      xz1=bzip2;;
+    *[-.][zZ] | *_z | *[-.]gz | *.t[ag]z)
+      xz1=gzip;;
+    *[-.]lzo | *.tzo)
+      xz1=lzop;;
+    *[-.]zst | *.tzst)
+      xz1='zstd -q';;
+    *)
+      printf '%s\n' "$0: $1: Unknown compressed file name suffix" >&2
+      exit 2;;
+  esac
+  case $1 in
+    *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *[-.]lzo | *[-.]zst)
+      FILE=`expr "X$1" : 'X\(.*\)[-.][abglmostxzZ2]*$'`;;
+    *.t[abglx]z)
+      FILE=`expr "X$1" : 'X\(.*[-.]t\)[abglx]z$'`ar;;
+    *.tbz2)
+      FILE=`expr "X$1" : 'X\(.*[-.]t\)bz2$'`ar;;
+    *.tzo)
+      FILE=`expr "X$1" : 'X\(.*[-.]t\)zo$'`ar;;
+    *.tzst)
+      FILE=`expr "X$1" : 'X\(.*[-.]t\)zst$'`ar;;
+  esac
+  xz_status=$(
+    exec 4>&1
+    ($xz1 -cd -- "$1" 4>&-; echo $? >&4) 3>&- | eval "$cmp" - '"$FILE"' >&3
+  )
+elif test $# -eq 2; then
+  case $1 in
+    *[-.]bz2 | *.tbz | *.tbz2) xz1=bzip2;;
+    *[-.][zZ] | *_z | *[-.]gz | *.t[ag]z) xz1=gzip;;
+    *[-.]lzo | *.tzo) xz1=lzop;;
+    *[-.]zst | *.tzst) xz1='zstd -q';;
+  esac
+  case $2 in
+    *[-.]bz2 | *.tbz | *.tbz2) xz2=bzip2;;
+    *[-.][zZ] | *_z | *[-.]gz | *.t[ag]z) xz2=gzip;;
+    *[-.]lzo | *.tzo) xz2=lzop;;
+    *[-.]zst | *.tzst) xz2='zstd -q';;
+  esac
+  case $1 in
+    *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | -)
+      case "$2" in
+        *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | -)
+          if test "$1$2" = --; then
+            xz_status=$(
+              exec 4>&1
+              ($xz1 -cdf - 4>&-; echo $? >&4) 3>&- |
+                eval "$cmp" - - >&3
+            )
+          elif # Reject Solaris 8's buggy /bin/bash 2.03.
+              echo X | (echo X | eval "$cmp" /dev/fd/5 - >/dev/null 2>&1) 5<&0; then
+            # NOTE: xz_status will contain two numbers.
+            xz_status=$(
+              exec 4>&1
+              ($xz1 -cdf -- "$1" 4>&-; echo $? >&4) 3>&- |
+                ( ($xz2 -cdf -- "$2" 4>&-; echo $? >&4) 3>&- 5<&- </dev/null |
+                eval "$cmp" /dev/fd/5 - >&3) 5<&0
+            )
+          else
+            F=`expr "/$2" : '.*/\(.*\)[-.][ablmotxz2]*$'` || F=$prog
+            tmp=
+            trap '
+              test -n "$tmp" && rm -rf "$tmp"
+              (exit 2); exit 2
+            ' HUP INT PIPE TERM 0
+            if type mktemp >/dev/null 2>&1; then
+              # Note that FreeBSD's mktemp isn't fully compatible with
+              # the implementations from mktemp.org and GNU coreutils.
+              # It is important that the -t argument is the last argument
+              # and that no "--" is used between -t and the template argument.
+              # This way this command works on all implementations.
+              tmp=`mktemp -d -t "$prog.XXXXXXXXXX"` || exit 2
+            else
+              # Fallback code if mktemp is missing. This isn't as
+              # robust as using mktemp since this doesn't try with
+              # different file names in case of a file name conflict.
+              #
+              # There's no need to save the original umask since
+              # we don't create any non-temp files. Note that using
+              # mkdir -m 0077 isn't secure since some mkdir implementations
+              # create the dir with the default umask and chmod the
+              # the dir afterwards.
+              umask 0077
+              mkdir -- "${TMPDIR-/tmp}/$prog.$$" || exit 2
+              tmp="${TMPDIR-/tmp}/$prog.$$"
+            fi
+            $xz2 -cdf -- "$2" > "$tmp/$F" || exit 2
+            xz_status=$(
+              exec 4>&1
+              ($xz1 -cdf -- "$1" 4>&-; echo $? >&4) 3>&- |
+                eval "$cmp" - '"$tmp/$F"' >&3
+            )
+            cmp_status=$?
+            rm -rf "$tmp" || xz_status=$?
+            trap - HUP INT PIPE TERM 0
+            (exit $cmp_status)
+          fi;;
+      *)
+        xz_status=$(
+          exec 4>&1
+          ($xz1 -cdf -- "$1" 4>&-; echo $? >&4) 3>&- |
+            eval "$cmp" - '"$2"' >&3
+        );;
+    esac;;
+  *)
+    case "$2" in
+      *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | -)
+        xz_status=$(
+          exec 4>&1
+          ($xz2 -cdf -- "$2" 4>&-; echo $? >&4) 3>&- |
+            eval "$cmp" '"$1"' - >&3
+         );;
+      *)
+        eval "$cmp" '"$1"' '"$2"';;
+    esac;;
+  esac
+else
+  printf '%s\n' "$0: Invalid number of operands; try \`${0##*/} --help' for help" >&2
+  exit 2
+fi
+
+cmp_status=$?
+for num in $xz_status ; do
+  # 0 from decompressor means successful decompression. SIGPIPE from
+  # decompressor is possible when diff or cmp exits before the whole file
+  # has been decompressed. In that case we want to retain the exit status
+  # from diff or cmp. Note that using "trap '' PIPE" is not possible
+  # because gzip changes its behavior (including exit status) if SIGPIPE
+  # is ignored.
+  test "$num" -eq 0 && continue
+  test "$num" -ge 128 \
+      && test "$(kill -l "$num" 2> /dev/null)" = "PIPE" \
+      && continue
+  exit 2
+done
+exit $cmp_status

ocr-application/bin/lzdiff

@@ -0,0 +1,215 @@
+#!/bin/sh
+
+# Copyright (C) 1998, 2002, 2006, 2007 Free Software Foundation
+# Copyright (C) 1993 Jean-loup Gailly
+
+# Modified for XZ Utils by Andrew Dudman and Lasse Collin.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT. With gzip, bzip2, and lzop it's OK to just unset the
+# environment variables.
+xz='xz --format=auto'
+unset GZIP BZIP BZIP2 LZOP
+
+case ${0##*/} in
+  *cmp*) prog=xzcmp; cmp=${CMP:-cmp};;
+  *)     prog=xzdiff; cmp=${DIFF:-diff};;
+esac
+
+version="$prog (XZ Utils) 5.4.6"
+
+usage="Usage: ${0##*/} [OPTION]... FILE1 [FILE2]
+Compare FILE1 to FILE2, using their uncompressed contents if they are
+compressed.  If FILE2 is omitted, then the files compared are FILE1 and
+FILE1 from which the compression format suffix has been stripped.
+
+Do comparisons like '$cmp' does.  OPTIONs are the same as for '$cmp'.
+
+Report bugs to <xz@tukaani.org>."
+
+# sed script to escape all ' for the shell, and then (to handle trailing
+# newlines correctly) turn trailing X on last line into '.
+escape='
+  s/'\''/'\''\\'\'''\''/g
+  $s/X$/'\''/
+'
+
+while :; do
+  case $1 in
+    --h*) printf '%s\n' "$usage" || exit 2; exit;;
+    --v*) printf '%s\n' "$version" || exit 2; exit;;
+    --) shift; break;;
+    -*\'*) cmp="$cmp '"`printf '%sX\n' "$1" | sed "$escape"`;;
+    -?*) cmp="$cmp '$1'";;
+    *) break;;
+  esac
+  shift
+done
+cmp="$cmp --"
+
+for file; do
+  test "X$file" = X- || <"$file" || exit 2
+done
+
+# xz needs -qQ to ignore warnings like unsupported check type.
+xz1="$xz -qQ"
+xz2="$xz -qQ"
+xz_status=0
+exec 3>&1
+
+if test $# -eq 1; then
+  case $1 in
+    *[-.]xz | *[-.]lzma | *[-.]lz | *.t[lx]z)
+      ;;
+    *[-.]bz2 | *.tbz | *.tbz2)
+      xz1=bzip2;;
+    *[-.][zZ] | *_z | *[-.]gz | *.t[ag]z)
+      xz1=gzip;;
+    *[-.]lzo | *.tzo)
+      xz1=lzop;;
+    *[-.]zst | *.tzst)
+      xz1='zstd -q';;
+    *)
+      printf '%s\n' "$0: $1: Unknown compressed file name suffix" >&2
+      exit 2;;
+  esac
+  case $1 in
+    *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *[-.]lzo | *[-.]zst)
+      FILE=`expr "X$1" : 'X\(.*\)[-.][abglmostxzZ2]*$'`;;
+    *.t[abglx]z)
+      FILE=`expr "X$1" : 'X\(.*[-.]t\)[abglx]z$'`ar;;
+    *.tbz2)
+      FILE=`expr "X$1" : 'X\(.*[-.]t\)bz2$'`ar;;
+    *.tzo)
+      FILE=`expr "X$1" : 'X\(.*[-.]t\)zo$'`ar;;
+    *.tzst)
+      FILE=`expr "X$1" : 'X\(.*[-.]t\)zst$'`ar;;
+  esac
+  xz_status=$(
+    exec 4>&1
+    ($xz1 -cd -- "$1" 4>&-; echo $? >&4) 3>&- | eval "$cmp" - '"$FILE"' >&3
+  )
+elif test $# -eq 2; then
+  case $1 in
+    *[-.]bz2 | *.tbz | *.tbz2) xz1=bzip2;;
+    *[-.][zZ] | *_z | *[-.]gz | *.t[ag]z) xz1=gzip;;
+    *[-.]lzo | *.tzo) xz1=lzop;;
+    *[-.]zst | *.tzst) xz1='zstd -q';;
+  esac
+  case $2 in
+    *[-.]bz2 | *.tbz | *.tbz2) xz2=bzip2;;
+    *[-.][zZ] | *_z | *[-.]gz | *.t[ag]z) xz2=gzip;;
+    *[-.]lzo | *.tzo) xz2=lzop;;
+    *[-.]zst | *.tzst) xz2='zstd -q';;
+  esac
+  case $1 in
+    *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | -)
+      case "$2" in
+        *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | -)
+          if test "$1$2" = --; then
+            xz_status=$(
+              exec 4>&1
+              ($xz1 -cdf - 4>&-; echo $? >&4) 3>&- |
+                eval "$cmp" - - >&3
+            )
+          elif # Reject Solaris 8's buggy /bin/bash 2.03.
+              echo X | (echo X | eval "$cmp" /dev/fd/5 - >/dev/null 2>&1) 5<&0; then
+            # NOTE: xz_status will contain two numbers.
+            xz_status=$(
+              exec 4>&1
+              ($xz1 -cdf -- "$1" 4>&-; echo $? >&4) 3>&- |
+                ( ($xz2 -cdf -- "$2" 4>&-; echo $? >&4) 3>&- 5<&- </dev/null |
+                eval "$cmp" /dev/fd/5 - >&3) 5<&0
+            )
+          else
+            F=`expr "/$2" : '.*/\(.*\)[-.][ablmotxz2]*$'` || F=$prog
+            tmp=
+            trap '
+              test -n "$tmp" && rm -rf "$tmp"
+              (exit 2); exit 2
+            ' HUP INT PIPE TERM 0
+            if type mktemp >/dev/null 2>&1; then
+              # Note that FreeBSD's mktemp isn't fully compatible with
+              # the implementations from mktemp.org and GNU coreutils.
+              # It is important that the -t argument is the last argument
+              # and that no "--" is used between -t and the template argument.
+              # This way this command works on all implementations.
+              tmp=`mktemp -d -t "$prog.XXXXXXXXXX"` || exit 2
+            else
+              # Fallback code if mktemp is missing. This isn't as
+              # robust as using mktemp since this doesn't try with
+              # different file names in case of a file name conflict.
+              #
+              # There's no need to save the original umask since
+              # we don't create any non-temp files. Note that using
+              # mkdir -m 0077 isn't secure since some mkdir implementations
+              # create the dir with the default umask and chmod the
+              # the dir afterwards.
+              umask 0077
+              mkdir -- "${TMPDIR-/tmp}/$prog.$$" || exit 2
+              tmp="${TMPDIR-/tmp}/$prog.$$"
+            fi
+            $xz2 -cdf -- "$2" > "$tmp/$F" || exit 2
+            xz_status=$(
+              exec 4>&1
+              ($xz1 -cdf -- "$1" 4>&-; echo $? >&4) 3>&- |
+                eval "$cmp" - '"$tmp/$F"' >&3
+            )
+            cmp_status=$?
+            rm -rf "$tmp" || xz_status=$?
+            trap - HUP INT PIPE TERM 0
+            (exit $cmp_status)
+          fi;;
+      *)
+        xz_status=$(
+          exec 4>&1
+          ($xz1 -cdf -- "$1" 4>&-; echo $? >&4) 3>&- |
+            eval "$cmp" - '"$2"' >&3
+        );;
+    esac;;
+  *)
+    case "$2" in
+      *[-.][zZ] | *_z | *[-.][gx]z | *[-.]bz2 | *[-.]lzma | *[-.]lz | *.t[abglx]z | *.tbz2 | *[-.]lzo | *.tzo | *[-.]zst | *.tzst | -)
+        xz_status=$(
+          exec 4>&1
+          ($xz2 -cdf -- "$2" 4>&-; echo $? >&4) 3>&- |
+            eval "$cmp" '"$1"' - >&3
+         );;
+      *)
+        eval "$cmp" '"$1"' '"$2"';;
+    esac;;
+  esac
+else
+  printf '%s\n' "$0: Invalid number of operands; try \`${0##*/} --help' for help" >&2
+  exit 2
+fi
+
+cmp_status=$?
+for num in $xz_status ; do
+  # 0 from decompressor means successful decompression. SIGPIPE from
+  # decompressor is possible when diff or cmp exits before the whole file
+  # has been decompressed. In that case we want to retain the exit status
+  # from diff or cmp. Note that using "trap '' PIPE" is not possible
+  # because gzip changes its behavior (including exit status) if SIGPIPE
+  # is ignored.
+  test "$num" -eq 0 && continue
+  test "$num" -ge 128 \
+      && test "$(kill -l "$num" 2> /dev/null)" = "PIPE" \
+      && continue
+  exit 2
+done
+exit $cmp_status

ocr-application/bin/lzegrep

@@ -0,0 +1,298 @@
+#!/bin/sh
+
+# xzgrep -- a wrapper around a grep program that decompresses files as needed
+# Adapted from a version sent by Charles Levert <charles@comm.polymtl.ca>
+
+# Copyright (C) 1998, 2001, 2002, 2006, 2007 Free Software Foundation
+# Copyright (C) 1993 Jean-loup Gailly
+
+# Modified for XZ Utils by Andrew Dudman and Lasse Collin.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT. With gzip, bzip2, and lzop it's OK to just unset the
+# environment variables.
+xz='xz --format=auto'
+unset GZIP BZIP BZIP2 LZOP
+
+case ${0##*/} in
+  *egrep*) prog=xzegrep; grep=${GREP:-grep -E};;
+  *fgrep*) prog=xzfgrep; grep=${GREP:-grep -F};;
+  *)       prog=xzgrep; grep=${GREP:-grep};;
+esac
+
+version="$prog (XZ Utils) 5.4.6"
+
+usage="Usage: ${0##*/} [OPTION]... [-e] PATTERN [FILE]...
+Look for instances of PATTERN in the input FILEs, using their
+uncompressed contents if they are compressed.
+
+OPTIONs are the same as for '$grep'.
+
+Report bugs to <xz@tukaani.org>."
+
+# sed script to escape all ' for the shell, and then (to handle trailing
+# newlines correctly) turn trailing X on last line into '.
+escape='
+  s/'\''/'\''\\'\'''\''/g
+  $s/X$/'\''/
+'
+operands=
+have_pat=0
+files_with_matches=0
+files_without_matches=0
+no_filename=0
+with_filename=0
+
+# See if -H and --label options are supported (GNU and *BSDs).
+if test f:x = "$(eval "echo x | $grep -H --label=f x 2> /dev/null")"; then
+  grep_supports_label=1
+else
+  grep_supports_label=0
+fi
+
+while test $# -ne 0; do
+  option=$1
+  shift
+  optarg=
+
+  case $option in
+  (-[0123456789abcdEFGhHiIKlLnoPqrRsTuUvVwxyzZ]*[!0123456789]*)
+    # Something like -Fiv was specified, that is, $option contains more
+    # than one option of which the first option (in this example -F)
+    # doesn't take an argument. Split the first option into a standalone
+    # argument and continue parsing the rest of the options (in this example,
+    # replace -Fiv with -iv in the argument list and set option=-F).
+    #
+    # If there are digits [0-9] they are treated as if they were a single
+    # option character because this syntax is an alias for -C for GNU grep.
+    # For example, "grep -25F" is equivalent to "grep -C25 -F". If only
+    # digits are specified like "grep -25" we don't get here because the
+    # above pattern in the case-statement doesn't match such strings.
+    arg2=-\'$(LC_ALL=C expr "X${option}X" : 'X-.[0-9]*\(.*\)' |
+                LC_ALL=C sed "$escape")
+    eval "set -- $arg2 "'${1+"$@"}'
+    option=$(LC_ALL=C expr "X$option" : 'X\(-.[0-9]*\)');;
+  (--binary-*=* | --[lm]a*=* | --reg*=*)
+    # These options require an argument and an argument has been provided
+    # with the --foo=argument syntax. All is good.
+    ;;
+  (-[ABCDefmX] | --binary-* | --file | --[lm]a* | --reg*)
+    # These options require an argument which should now be in $1.
+    # If it isn't, display an error and exit.
+    case ${1?"$option option requires an argument"} in
+    (*\'*)
+      optarg=" '"$(printf '%sX\n' "$1" | LC_ALL=C sed "$escape");;
+    (*)
+      optarg=" '$1'";;
+    esac
+    shift;;
+  (--)
+    break;;
+  (-?*)
+    ;;
+  (*)
+    case $option in
+    (*\'*)
+      operands="$operands '"$(printf '%sX\n' "$option" |
+                                LC_ALL=C sed "$escape");;
+    (*)
+      operands="$operands '$option'";;
+    esac
+    ${POSIXLY_CORRECT+break}
+    continue;;
+  esac
+
+  case $option in
+  (-[drRzZ] | --di* | --exc* | --inc* | --rec* | --nu*)
+    printf >&2 '%s: %s: Option not supported\n' "$0" "$option"
+    exit 2;;
+  (-[ef]* | --file | --file=* | --reg*)
+    have_pat=1;;
+  (--h | --he | --hel | --help)
+    printf '%s\n' "$usage" || exit 2
+    exit;;
+  (-H | --wi | --wit | --with | --with- | --with-f | --with-fi \
+  | --with-fil | --with-file | --with-filen | --with-filena | --with-filenam \
+  | --with-filename)
+    with_filename=1
+    continue;;
+  (-l | --files-with-*)
+    files_with_matches=1
+    continue;;
+  (-L | --files-witho*)
+    files_without_matches=1
+    continue;;
+  (-h | --no-f*)
+    no_filename=1;;
+  (-V | --v | --ve | --ver | --vers | --versi | --versio | --version)
+    printf '%s\n' "$version" || exit 2
+    exit;;
+  esac
+
+  case $option in
+  (*\'?*)
+    option=\'$(printf '%sX\n' "$option" | LC_ALL=C sed "$escape");;
+  (*)
+    option="'$option'";;
+  esac
+
+  grep="$grep $option$optarg"
+done
+
+eval "set -- $operands "'${1+"$@"}'
+
+if test $have_pat -eq 0; then
+  case ${1?"Missing pattern; try \`${0##*/} --help' for help"} in
+  (*\'*)
+    grep="$grep -e '"$(printf '%sX\n' "$1" | LC_ALL=C sed "$escape");;
+  (*)
+    grep="$grep -e '$1'";;
+  esac
+  shift
+fi
+
+if test $# -eq 0; then
+  set -- -
+fi
+
+exec 3>&1
+
+# res=1 means that no file matched yet
+res=1
+
+for i; do
+  case $i in
+    *[-.][zZ] | *_z | *[-.]gz | *.t[ag]z) uncompress="gzip -cdf";;
+    *[-.]bz2 | *[-.]tbz | *.tbz2) uncompress="bzip2 -cdf";;
+    *[-.]lzo | *[-.]tzo) uncompress="lzop -cdf";;
+    *[-.]zst | *[-.]tzst) uncompress="zstd -cdfq";; # zstd needs -q.
+    *) uncompress="$xz -cdfqQ";; # -qQ to ignore warnings like unsupp. check.
+  esac
+  # xz_status will hold the decompressor's exit status.
+  # Exit status of grep (and in rare cases, printf or sed) is
+  # available as the exit status of this assignment command.
+  xz_status=$(
+    exec 5>&1
+    ($uncompress -- "$i" 5>&-; echo $? >&5) 3>&- |
+    if test $files_with_matches -eq 1; then
+      eval "$grep -q" && { printf '%s\n' "$i" || exit 2; }
+    elif test $files_without_matches -eq 1; then
+      eval "$grep -q" || {
+        r=$?
+        if test $r -eq 1; then
+          printf '%s\n' "$i" || r=2
+        fi
+        exit $r
+      }
+    elif test $with_filename -eq 0 &&
+         { test $# -eq 1 || test $no_filename -eq 1; }; then
+      eval "$grep"
+    elif test $grep_supports_label -eq 1; then
+      # The grep implementation in use allows us to specify the filename
+      # that grep will prefix to the output lines. This is faster and
+      # less prone to security bugs than the fallback method that uses sed.
+      # This also avoids confusing output with GNU grep >= 3.5 (2020-09-27)
+      # which prints "binary file matches" to stderr instead of stdout.
+      #
+      # If reading from stdin, let grep use whatever name it prefers for
+      # stdin. With GNU grep it is a locale-specific translated string.
+      if test "x$i" = "x-"; then
+        eval "$grep -H"
+      else
+        eval "$grep -H --label \"\$i\""
+      fi
+    else
+      # Append a colon so that the last character will never be a newline
+      # which would otherwise get lost in shell command substitution.
+      i="$i:"
+
+      # Escape & \ | and newlines only if such characters are present
+      # (speed optimization).
+      case $i in
+      (*'
+'* | *'&'* | *'\'* | *'|'*)
+        # If sed fails, set i to a known safe string to ensure that
+        # failing sed did not create a half-escaped dangerous string.
+        i=$(printf '%s\n' "$i" | LC_ALL=C sed 's/[&\|]/\\&/g; $!s/$/\\/') ||
+            i='(unknown filename):';;
+      esac
+
+      # $i already ends with a colon so do not add it here.
+      sed_script="s|^|$i|"
+
+      # If grep or sed fails, pick the larger value of the two exit statuses.
+      # If sed fails, use at least 2 since we use >= 2 to indicate errors.
+      r=$(
+        exec 4>&1
+        (eval "$grep" 4>&-; echo $? >&4) 3>&- |
+            LC_ALL=C sed "$sed_script" >&3 4>&-
+      ) || {
+        sed_status=$?
+        test "$sed_status" -lt 2 && sed_status=2
+        test "$r" -lt "$sed_status" && r=$sed_status
+      }
+      exit $r
+    fi >&3 5>&-
+  )
+  r=$?
+
+  # If grep or sed or other non-decompression command failed with a signal,
+  # exit immediately and ignore the possible remaining files.
+  #
+  # NOTE: Instead of 128 + signal_number, some shells use
+  # 256 + signal_number (ksh) or 384 + signal_number (yash).
+  # This is fine for us since their "exit" and "kill -l" commands take
+  # this into account. (At least the versions I tried do but there is
+  # a report of an old ksh variant whose "exit" truncates the exit status
+  # to 8 bits without any special handling for values indicating a signal.)
+  test "$r" -ge 128 && exit "$r"
+
+  if test -z "$xz_status"; then
+    # Something unusual happened, for example, we got a signal and
+    # the exit status of the decompressor was never echoed and thus
+    # $xz_status is empty. Exit immediately and ignore the possible
+    # remaining files.
+    exit 2
+  elif test "$xz_status" -ge 128; then
+    # The decompressor died due to a signal. SIGPIPE is ignored since it can
+    # occur if grep exits before the whole file has been decompressed (grep -q
+    # can do that). If the decompressor died with some other signal, exit
+    # immediately and ignore the possible remaining files.
+    test "$(kill -l "$xz_status" 2> /dev/null)" != "PIPE" && exit "$xz_status"
+  elif test "$xz_status" -gt 0; then
+    # Decompression failed but we will continue with the remaining
+    # files anwyway. Set exit status to at least 2 to indicate an error.
+    test "$r" -lt 2 && r=2
+  fi
+
+  # Since res=1 is the initial value, we only need to care about
+  # matches (r == 0) and errors (r >= 2) here; r == 1 can be ignored.
+  if test "$r" -ge 2; then
+    # An error occurred in decompressor, grep, or some other command. Update
+    # res unless a larger error code has been seen with an earlier file.
+    test "$res" -lt "$r" && res=$r
+  elif test "$r" -eq 0; then
+    # grep found a match and no errors occurred. Update res if no errors have
+    # occurred with earlier files.
+    test "$res" -eq 1 && res=0
+  fi
+done
+
+# 0: At least one file matched and no errors occurred.
+# 1: No matches were found and no errors occurred.
+# >=2: Error. It's unknown if matches were found.
+exit "$res"

ocr-application/bin/lzfgrep

@@ -0,0 +1,298 @@
+#!/bin/sh
+
+# xzgrep -- a wrapper around a grep program that decompresses files as needed
+# Adapted from a version sent by Charles Levert <charles@comm.polymtl.ca>
+
+# Copyright (C) 1998, 2001, 2002, 2006, 2007 Free Software Foundation
+# Copyright (C) 1993 Jean-loup Gailly
+
+# Modified for XZ Utils by Andrew Dudman and Lasse Collin.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT. With gzip, bzip2, and lzop it's OK to just unset the
+# environment variables.
+xz='xz --format=auto'
+unset GZIP BZIP BZIP2 LZOP
+
+case ${0##*/} in
+  *egrep*) prog=xzegrep; grep=${GREP:-grep -E};;
+  *fgrep*) prog=xzfgrep; grep=${GREP:-grep -F};;
+  *)       prog=xzgrep; grep=${GREP:-grep};;
+esac
+
+version="$prog (XZ Utils) 5.4.6"
+
+usage="Usage: ${0##*/} [OPTION]... [-e] PATTERN [FILE]...
+Look for instances of PATTERN in the input FILEs, using their
+uncompressed contents if they are compressed.
+
+OPTIONs are the same as for '$grep'.
+
+Report bugs to <xz@tukaani.org>."
+
+# sed script to escape all ' for the shell, and then (to handle trailing
+# newlines correctly) turn trailing X on last line into '.
+escape='
+  s/'\''/'\''\\'\'''\''/g
+  $s/X$/'\''/
+'
+operands=
+have_pat=0
+files_with_matches=0
+files_without_matches=0
+no_filename=0
+with_filename=0
+
+# See if -H and --label options are supported (GNU and *BSDs).
+if test f:x = "$(eval "echo x | $grep -H --label=f x 2> /dev/null")"; then
+  grep_supports_label=1
+else
+  grep_supports_label=0
+fi
+
+while test $# -ne 0; do
+  option=$1
+  shift
+  optarg=
+
+  case $option in
+  (-[0123456789abcdEFGhHiIKlLnoPqrRsTuUvVwxyzZ]*[!0123456789]*)
+    # Something like -Fiv was specified, that is, $option contains more
+    # than one option of which the first option (in this example -F)
+    # doesn't take an argument. Split the first option into a standalone
+    # argument and continue parsing the rest of the options (in this example,
+    # replace -Fiv with -iv in the argument list and set option=-F).
+    #
+    # If there are digits [0-9] they are treated as if they were a single
+    # option character because this syntax is an alias for -C for GNU grep.
+    # For example, "grep -25F" is equivalent to "grep -C25 -F". If only
+    # digits are specified like "grep -25" we don't get here because the
+    # above pattern in the case-statement doesn't match such strings.
+    arg2=-\'$(LC_ALL=C expr "X${option}X" : 'X-.[0-9]*\(.*\)' |
+                LC_ALL=C sed "$escape")
+    eval "set -- $arg2 "'${1+"$@"}'
+    option=$(LC_ALL=C expr "X$option" : 'X\(-.[0-9]*\)');;
+  (--binary-*=* | --[lm]a*=* | --reg*=*)
+    # These options require an argument and an argument has been provided
+    # with the --foo=argument syntax. All is good.
+    ;;
+  (-[ABCDefmX] | --binary-* | --file | --[lm]a* | --reg*)
+    # These options require an argument which should now be in $1.
+    # If it isn't, display an error and exit.
+    case ${1?"$option option requires an argument"} in
+    (*\'*)
+      optarg=" '"$(printf '%sX\n' "$1" | LC_ALL=C sed "$escape");;
+    (*)
+      optarg=" '$1'";;
+    esac
+    shift;;
+  (--)
+    break;;
+  (-?*)
+    ;;
+  (*)
+    case $option in
+    (*\'*)
+      operands="$operands '"$(printf '%sX\n' "$option" |
+                                LC_ALL=C sed "$escape");;
+    (*)
+      operands="$operands '$option'";;
+    esac
+    ${POSIXLY_CORRECT+break}
+    continue;;
+  esac
+
+  case $option in
+  (-[drRzZ] | --di* | --exc* | --inc* | --rec* | --nu*)
+    printf >&2 '%s: %s: Option not supported\n' "$0" "$option"
+    exit 2;;
+  (-[ef]* | --file | --file=* | --reg*)
+    have_pat=1;;
+  (--h | --he | --hel | --help)
+    printf '%s\n' "$usage" || exit 2
+    exit;;
+  (-H | --wi | --wit | --with | --with- | --with-f | --with-fi \
+  | --with-fil | --with-file | --with-filen | --with-filena | --with-filenam \
+  | --with-filename)
+    with_filename=1
+    continue;;
+  (-l | --files-with-*)
+    files_with_matches=1
+    continue;;
+  (-L | --files-witho*)
+    files_without_matches=1
+    continue;;
+  (-h | --no-f*)
+    no_filename=1;;
+  (-V | --v | --ve | --ver | --vers | --versi | --versio | --version)
+    printf '%s\n' "$version" || exit 2
+    exit;;
+  esac
+
+  case $option in
+  (*\'?*)
+    option=\'$(printf '%sX\n' "$option" | LC_ALL=C sed "$escape");;
+  (*)
+    option="'$option'";;
+  esac
+
+  grep="$grep $option$optarg"
+done
+
+eval "set -- $operands "'${1+"$@"}'
+
+if test $have_pat -eq 0; then
+  case ${1?"Missing pattern; try \`${0##*/} --help' for help"} in
+  (*\'*)
+    grep="$grep -e '"$(printf '%sX\n' "$1" | LC_ALL=C sed "$escape");;
+  (*)
+    grep="$grep -e '$1'";;
+  esac
+  shift
+fi
+
+if test $# -eq 0; then
+  set -- -
+fi
+
+exec 3>&1
+
+# res=1 means that no file matched yet
+res=1
+
+for i; do
+  case $i in
+    *[-.][zZ] | *_z | *[-.]gz | *.t[ag]z) uncompress="gzip -cdf";;
+    *[-.]bz2 | *[-.]tbz | *.tbz2) uncompress="bzip2 -cdf";;
+    *[-.]lzo | *[-.]tzo) uncompress="lzop -cdf";;
+    *[-.]zst | *[-.]tzst) uncompress="zstd -cdfq";; # zstd needs -q.
+    *) uncompress="$xz -cdfqQ";; # -qQ to ignore warnings like unsupp. check.
+  esac
+  # xz_status will hold the decompressor's exit status.
+  # Exit status of grep (and in rare cases, printf or sed) is
+  # available as the exit status of this assignment command.
+  xz_status=$(
+    exec 5>&1
+    ($uncompress -- "$i" 5>&-; echo $? >&5) 3>&- |
+    if test $files_with_matches -eq 1; then
+      eval "$grep -q" && { printf '%s\n' "$i" || exit 2; }
+    elif test $files_without_matches -eq 1; then
+      eval "$grep -q" || {
+        r=$?
+        if test $r -eq 1; then
+          printf '%s\n' "$i" || r=2
+        fi
+        exit $r
+      }
+    elif test $with_filename -eq 0 &&
+         { test $# -eq 1 || test $no_filename -eq 1; }; then
+      eval "$grep"
+    elif test $grep_supports_label -eq 1; then
+      # The grep implementation in use allows us to specify the filename
+      # that grep will prefix to the output lines. This is faster and
+      # less prone to security bugs than the fallback method that uses sed.
+      # This also avoids confusing output with GNU grep >= 3.5 (2020-09-27)
+      # which prints "binary file matches" to stderr instead of stdout.
+      #
+      # If reading from stdin, let grep use whatever name it prefers for
+      # stdin. With GNU grep it is a locale-specific translated string.
+      if test "x$i" = "x-"; then
+        eval "$grep -H"
+      else
+        eval "$grep -H --label \"\$i\""
+      fi
+    else
+      # Append a colon so that the last character will never be a newline
+      # which would otherwise get lost in shell command substitution.
+      i="$i:"
+
+      # Escape & \ | and newlines only if such characters are present
+      # (speed optimization).
+      case $i in
+      (*'
+'* | *'&'* | *'\'* | *'|'*)
+        # If sed fails, set i to a known safe string to ensure that
+        # failing sed did not create a half-escaped dangerous string.
+        i=$(printf '%s\n' "$i" | LC_ALL=C sed 's/[&\|]/\\&/g; $!s/$/\\/') ||
+            i='(unknown filename):';;
+      esac
+
+      # $i already ends with a colon so do not add it here.
+      sed_script="s|^|$i|"
+
+      # If grep or sed fails, pick the larger value of the two exit statuses.
+      # If sed fails, use at least 2 since we use >= 2 to indicate errors.
+      r=$(
+        exec 4>&1
+        (eval "$grep" 4>&-; echo $? >&4) 3>&- |
+            LC_ALL=C sed "$sed_script" >&3 4>&-
+      ) || {
+        sed_status=$?
+        test "$sed_status" -lt 2 && sed_status=2
+        test "$r" -lt "$sed_status" && r=$sed_status
+      }
+      exit $r
+    fi >&3 5>&-
+  )
+  r=$?
+
+  # If grep or sed or other non-decompression command failed with a signal,
+  # exit immediately and ignore the possible remaining files.
+  #
+  # NOTE: Instead of 128 + signal_number, some shells use
+  # 256 + signal_number (ksh) or 384 + signal_number (yash).
+  # This is fine for us since their "exit" and "kill -l" commands take
+  # this into account. (At least the versions I tried do but there is
+  # a report of an old ksh variant whose "exit" truncates the exit status
+  # to 8 bits without any special handling for values indicating a signal.)
+  test "$r" -ge 128 && exit "$r"
+
+  if test -z "$xz_status"; then
+    # Something unusual happened, for example, we got a signal and
+    # the exit status of the decompressor was never echoed and thus
+    # $xz_status is empty. Exit immediately and ignore the possible
+    # remaining files.
+    exit 2
+  elif test "$xz_status" -ge 128; then
+    # The decompressor died due to a signal. SIGPIPE is ignored since it can
+    # occur if grep exits before the whole file has been decompressed (grep -q
+    # can do that). If the decompressor died with some other signal, exit
+    # immediately and ignore the possible remaining files.
+    test "$(kill -l "$xz_status" 2> /dev/null)" != "PIPE" && exit "$xz_status"
+  elif test "$xz_status" -gt 0; then
+    # Decompression failed but we will continue with the remaining
+    # files anwyway. Set exit status to at least 2 to indicate an error.
+    test "$r" -lt 2 && r=2
+  fi
+
+  # Since res=1 is the initial value, we only need to care about
+  # matches (r == 0) and errors (r >= 2) here; r == 1 can be ignored.
+  if test "$r" -ge 2; then
+    # An error occurred in decompressor, grep, or some other command. Update
+    # res unless a larger error code has been seen with an earlier file.
+    test "$res" -lt "$r" && res=$r
+  elif test "$r" -eq 0; then
+    # grep found a match and no errors occurred. Update res if no errors have
+    # occurred with earlier files.
+    test "$res" -eq 1 && res=0
+  fi
+done
+
+# 0: At least one file matched and no errors occurred.
+# 1: No matches were found and no errors occurred.
+# >=2: Error. It's unknown if matches were found.
+exit "$res"

ocr-application/bin/lzgrep

@@ -0,0 +1,298 @@
+#!/bin/sh
+
+# xzgrep -- a wrapper around a grep program that decompresses files as needed
+# Adapted from a version sent by Charles Levert <charles@comm.polymtl.ca>
+
+# Copyright (C) 1998, 2001, 2002, 2006, 2007 Free Software Foundation
+# Copyright (C) 1993 Jean-loup Gailly
+
+# Modified for XZ Utils by Andrew Dudman and Lasse Collin.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT. With gzip, bzip2, and lzop it's OK to just unset the
+# environment variables.
+xz='xz --format=auto'
+unset GZIP BZIP BZIP2 LZOP
+
+case ${0##*/} in
+  *egrep*) prog=xzegrep; grep=${GREP:-grep -E};;
+  *fgrep*) prog=xzfgrep; grep=${GREP:-grep -F};;
+  *)       prog=xzgrep; grep=${GREP:-grep};;
+esac
+
+version="$prog (XZ Utils) 5.4.6"
+
+usage="Usage: ${0##*/} [OPTION]... [-e] PATTERN [FILE]...
+Look for instances of PATTERN in the input FILEs, using their
+uncompressed contents if they are compressed.
+
+OPTIONs are the same as for '$grep'.
+
+Report bugs to <xz@tukaani.org>."
+
+# sed script to escape all ' for the shell, and then (to handle trailing
+# newlines correctly) turn trailing X on last line into '.
+escape='
+  s/'\''/'\''\\'\'''\''/g
+  $s/X$/'\''/
+'
+operands=
+have_pat=0
+files_with_matches=0
+files_without_matches=0
+no_filename=0
+with_filename=0
+
+# See if -H and --label options are supported (GNU and *BSDs).
+if test f:x = "$(eval "echo x | $grep -H --label=f x 2> /dev/null")"; then
+  grep_supports_label=1
+else
+  grep_supports_label=0
+fi
+
+while test $# -ne 0; do
+  option=$1
+  shift
+  optarg=
+
+  case $option in
+  (-[0123456789abcdEFGhHiIKlLnoPqrRsTuUvVwxyzZ]*[!0123456789]*)
+    # Something like -Fiv was specified, that is, $option contains more
+    # than one option of which the first option (in this example -F)
+    # doesn't take an argument. Split the first option into a standalone
+    # argument and continue parsing the rest of the options (in this example,
+    # replace -Fiv with -iv in the argument list and set option=-F).
+    #
+    # If there are digits [0-9] they are treated as if they were a single
+    # option character because this syntax is an alias for -C for GNU grep.
+    # For example, "grep -25F" is equivalent to "grep -C25 -F". If only
+    # digits are specified like "grep -25" we don't get here because the
+    # above pattern in the case-statement doesn't match such strings.
+    arg2=-\'$(LC_ALL=C expr "X${option}X" : 'X-.[0-9]*\(.*\)' |
+                LC_ALL=C sed "$escape")
+    eval "set -- $arg2 "'${1+"$@"}'
+    option=$(LC_ALL=C expr "X$option" : 'X\(-.[0-9]*\)');;
+  (--binary-*=* | --[lm]a*=* | --reg*=*)
+    # These options require an argument and an argument has been provided
+    # with the --foo=argument syntax. All is good.
+    ;;
+  (-[ABCDefmX] | --binary-* | --file | --[lm]a* | --reg*)
+    # These options require an argument which should now be in $1.
+    # If it isn't, display an error and exit.
+    case ${1?"$option option requires an argument"} in
+    (*\'*)
+      optarg=" '"$(printf '%sX\n' "$1" | LC_ALL=C sed "$escape");;
+    (*)
+      optarg=" '$1'";;
+    esac
+    shift;;
+  (--)
+    break;;
+  (-?*)
+    ;;
+  (*)
+    case $option in
+    (*\'*)
+      operands="$operands '"$(printf '%sX\n' "$option" |
+                                LC_ALL=C sed "$escape");;
+    (*)
+      operands="$operands '$option'";;
+    esac
+    ${POSIXLY_CORRECT+break}
+    continue;;
+  esac
+
+  case $option in
+  (-[drRzZ] | --di* | --exc* | --inc* | --rec* | --nu*)
+    printf >&2 '%s: %s: Option not supported\n' "$0" "$option"
+    exit 2;;
+  (-[ef]* | --file | --file=* | --reg*)
+    have_pat=1;;
+  (--h | --he | --hel | --help)
+    printf '%s\n' "$usage" || exit 2
+    exit;;
+  (-H | --wi | --wit | --with | --with- | --with-f | --with-fi \
+  | --with-fil | --with-file | --with-filen | --with-filena | --with-filenam \
+  | --with-filename)
+    with_filename=1
+    continue;;
+  (-l | --files-with-*)
+    files_with_matches=1
+    continue;;
+  (-L | --files-witho*)
+    files_without_matches=1
+    continue;;
+  (-h | --no-f*)
+    no_filename=1;;
+  (-V | --v | --ve | --ver | --vers | --versi | --versio | --version)
+    printf '%s\n' "$version" || exit 2
+    exit;;
+  esac
+
+  case $option in
+  (*\'?*)
+    option=\'$(printf '%sX\n' "$option" | LC_ALL=C sed "$escape");;
+  (*)
+    option="'$option'";;
+  esac
+
+  grep="$grep $option$optarg"
+done
+
+eval "set -- $operands "'${1+"$@"}'
+
+if test $have_pat -eq 0; then
+  case ${1?"Missing pattern; try \`${0##*/} --help' for help"} in
+  (*\'*)
+    grep="$grep -e '"$(printf '%sX\n' "$1" | LC_ALL=C sed "$escape");;
+  (*)
+    grep="$grep -e '$1'";;
+  esac
+  shift
+fi
+
+if test $# -eq 0; then
+  set -- -
+fi
+
+exec 3>&1
+
+# res=1 means that no file matched yet
+res=1
+
+for i; do
+  case $i in
+    *[-.][zZ] | *_z | *[-.]gz | *.t[ag]z) uncompress="gzip -cdf";;
+    *[-.]bz2 | *[-.]tbz | *.tbz2) uncompress="bzip2 -cdf";;
+    *[-.]lzo | *[-.]tzo) uncompress="lzop -cdf";;
+    *[-.]zst | *[-.]tzst) uncompress="zstd -cdfq";; # zstd needs -q.
+    *) uncompress="$xz -cdfqQ";; # -qQ to ignore warnings like unsupp. check.
+  esac
+  # xz_status will hold the decompressor's exit status.
+  # Exit status of grep (and in rare cases, printf or sed) is
+  # available as the exit status of this assignment command.
+  xz_status=$(
+    exec 5>&1
+    ($uncompress -- "$i" 5>&-; echo $? >&5) 3>&- |
+    if test $files_with_matches -eq 1; then
+      eval "$grep -q" && { printf '%s\n' "$i" || exit 2; }
+    elif test $files_without_matches -eq 1; then
+      eval "$grep -q" || {
+        r=$?
+        if test $r -eq 1; then
+          printf '%s\n' "$i" || r=2
+        fi
+        exit $r
+      }
+    elif test $with_filename -eq 0 &&
+         { test $# -eq 1 || test $no_filename -eq 1; }; then
+      eval "$grep"
+    elif test $grep_supports_label -eq 1; then
+      # The grep implementation in use allows us to specify the filename
+      # that grep will prefix to the output lines. This is faster and
+      # less prone to security bugs than the fallback method that uses sed.
+      # This also avoids confusing output with GNU grep >= 3.5 (2020-09-27)
+      # which prints "binary file matches" to stderr instead of stdout.
+      #
+      # If reading from stdin, let grep use whatever name it prefers for
+      # stdin. With GNU grep it is a locale-specific translated string.
+      if test "x$i" = "x-"; then
+        eval "$grep -H"
+      else
+        eval "$grep -H --label \"\$i\""
+      fi
+    else
+      # Append a colon so that the last character will never be a newline
+      # which would otherwise get lost in shell command substitution.
+      i="$i:"
+
+      # Escape & \ | and newlines only if such characters are present
+      # (speed optimization).
+      case $i in
+      (*'
+'* | *'&'* | *'\'* | *'|'*)
+        # If sed fails, set i to a known safe string to ensure that
+        # failing sed did not create a half-escaped dangerous string.
+        i=$(printf '%s\n' "$i" | LC_ALL=C sed 's/[&\|]/\\&/g; $!s/$/\\/') ||
+            i='(unknown filename):';;
+      esac
+
+      # $i already ends with a colon so do not add it here.
+      sed_script="s|^|$i|"
+
+      # If grep or sed fails, pick the larger value of the two exit statuses.
+      # If sed fails, use at least 2 since we use >= 2 to indicate errors.
+      r=$(
+        exec 4>&1
+        (eval "$grep" 4>&-; echo $? >&4) 3>&- |
+            LC_ALL=C sed "$sed_script" >&3 4>&-
+      ) || {
+        sed_status=$?
+        test "$sed_status" -lt 2 && sed_status=2
+        test "$r" -lt "$sed_status" && r=$sed_status
+      }
+      exit $r
+    fi >&3 5>&-
+  )
+  r=$?
+
+  # If grep or sed or other non-decompression command failed with a signal,
+  # exit immediately and ignore the possible remaining files.
+  #
+  # NOTE: Instead of 128 + signal_number, some shells use
+  # 256 + signal_number (ksh) or 384 + signal_number (yash).
+  # This is fine for us since their "exit" and "kill -l" commands take
+  # this into account. (At least the versions I tried do but there is
+  # a report of an old ksh variant whose "exit" truncates the exit status
+  # to 8 bits without any special handling for values indicating a signal.)
+  test "$r" -ge 128 && exit "$r"
+
+  if test -z "$xz_status"; then
+    # Something unusual happened, for example, we got a signal and
+    # the exit status of the decompressor was never echoed and thus
+    # $xz_status is empty. Exit immediately and ignore the possible
+    # remaining files.
+    exit 2
+  elif test "$xz_status" -ge 128; then
+    # The decompressor died due to a signal. SIGPIPE is ignored since it can
+    # occur if grep exits before the whole file has been decompressed (grep -q
+    # can do that). If the decompressor died with some other signal, exit
+    # immediately and ignore the possible remaining files.
+    test "$(kill -l "$xz_status" 2> /dev/null)" != "PIPE" && exit "$xz_status"
+  elif test "$xz_status" -gt 0; then
+    # Decompression failed but we will continue with the remaining
+    # files anwyway. Set exit status to at least 2 to indicate an error.
+    test "$r" -lt 2 && r=2
+  fi
+
+  # Since res=1 is the initial value, we only need to care about
+  # matches (r == 0) and errors (r >= 2) here; r == 1 can be ignored.
+  if test "$r" -ge 2; then
+    # An error occurred in decompressor, grep, or some other command. Update
+    # res unless a larger error code has been seen with an earlier file.
+    test "$res" -lt "$r" && res=$r
+  elif test "$r" -eq 0; then
+    # grep found a match and no errors occurred. Update res if no errors have
+    # occurred with earlier files.
+    test "$res" -eq 1 && res=0
+  fi
+done
+
+# 0: At least one file matched and no errors occurred.
+# 1: No matches were found and no errors occurred.
+# >=2: Error. It's unknown if matches were found.
+exit "$res"

ocr-application/bin/lzless

@@ -0,0 +1,59 @@
+#!/bin/sh
+
+# Copyright (C) 1998, 2002, 2006, 2007 Free Software Foundation
+
+# The original version for gzip was written by Paul Eggert.
+# Modified for XZ Utils by Andrew Dudman and Lasse Collin.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT.
+xz='xz --format=auto'
+
+version='xzless (XZ Utils) 5.4.6'
+
+usage="Usage: ${0##*/} [OPTION]... [FILE]...
+Like 'less', but operate on the uncompressed contents of xz compressed FILEs.
+
+Options are the same as for 'less'.
+
+Report bugs to <xz@tukaani.org>."
+
+case $1 in
+	--help)    printf '%s\n' "$usage" || exit 2; exit;;
+	--version) printf '%s\n' "$version" || exit 2; exit;;
+esac
+
+if test "${LESSMETACHARS+set}" != set; then
+	# Work around a bug in less 394 and earlier;
+	# it mishandles the metacharacters '$%=~'.
+	space=' '
+	tab='	'
+	nl='
+'
+	LESSMETACHARS="$space$tab$nl'"';*?"()<>[|&^`#\$%=~'
+fi
+
+if test "$(less -V | { read _ ver _ && echo ${ver%%.*}; })" -ge 429; then
+	# less 429 or later: LESSOPEN pipe will be used on
+	# standard input if $LESSOPEN begins with |-.
+	LESSOPEN="|-$xz -cdfqQ -- %s"
+else
+	LESSOPEN="|$xz -cdfqQ -- %s"
+fi
+export LESSMETACHARS LESSOPEN
+
+exec less "$@"

ocr-application/bin/lzmore

@@ -0,0 +1,79 @@
+#!/bin/sh
+
+# Copyright (C) 2001, 2002, 2007 Free Software Foundation
+# Copyright (C) 1992, 1993 Jean-loup Gailly
+
+# Modified for XZ Utils by Andrew Dudman and Lasse Collin.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+
+#SET_PATH - This line is a placeholder to ease patching this script.
+
+# Instead of unsetting XZ_OPT, just make sure that xz will use file format
+# autodetection. This way memory usage limit and thread limit can be
+# specified via XZ_OPT.
+xz='xz --format=auto'
+
+version='xzmore (XZ Utils) 5.4.6'
+
+usage="Usage: ${0##*/} [OPTION]... [FILE]...
+Like 'more', but operate on the uncompressed contents of xz compressed FILEs.
+
+Report bugs to <xz@tukaani.org>."
+
+case $1 in
+	--help)    printf '%s\n' "$usage" || exit 2; exit;;
+	--version) printf '%s\n' "$version" || exit 2; exit;;
+esac
+
+oldtty=`stty -g 2>/dev/null`
+if stty -cbreak 2>/dev/null; then
+	cb='cbreak'; ncb='-cbreak'
+else
+	# 'stty min 1' resets eof to ^a on both SunOS and SysV!
+	cb='min 1 -icanon'; ncb='icanon eof ^d'
+fi
+if test $? -eq 0 && test -n "$oldtty"; then
+	trap 'stty $oldtty 2>/dev/null; exit' 0 2 3 5 10 13 15
+else
+	trap 'stty $ncb echo 2>/dev/null; exit' 0 2 3 5 10 13 15
+fi
+
+if test $# = 0; then
+	if test -t 0; then
+		printf '%s\n' "$usage"; exit 1
+	else
+		$xz -cdfqQ | eval "${PAGER:-more}"
+	fi
+else
+	FIRST=1
+	for FILE; do
+		< "$FILE" || continue
+		if test $FIRST -eq 0; then
+			printf "%s--More--(Next file: %s)" "" "$FILE"
+			stty $cb -echo 2>/dev/null
+			ANS=`dd bs=1 count=1 2>/dev/null`
+			stty $ncb echo 2>/dev/null
+			echo " "
+			case "$ANS" in
+				[eq]) exit;;
+			esac
+		fi
+		if test "$ANS" != 's'; then
+			printf '%s\n' "------> $FILE <------"
+			$xz -cdfqQ -- "$FILE" | eval "${PAGER:-more}"
+		fi
+		if test -t 1; then
+			FIRST=0
+		fi
+	done
+fi

ocr-application/bin/markdown-it

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from markdown_it.cli.parse import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

ocr-application/bin/ncursesw6-config

@@ -0,0 +1,331 @@
+#!/bin/sh
+# $Id: ncurses-config.in,v 1.52 2022/07/26 21:36:28 tom Exp $
+##############################################################################
+# Copyright 2018-2021,2022 Thomas E. Dickey                                  #
+# Copyright 2006-2015,2017 Free Software Foundation, Inc.                    #
+#                                                                            #
+# Permission is hereby granted, free of charge, to any person obtaining a    #
+# copy of this software and associated documentation files (the "Software"), #
+# to deal in the Software without restriction, including without limitation  #
+# the rights to use, copy, modify, merge, publish, distribute, distribute    #
+# with modifications, sublicense, and/or sell copies of the Software, and to #
+# permit persons to whom the Software is furnished to do so, subject to the  #
+# following conditions:                                                      #
+#                                                                            #
+# The above copyright notice and this permission notice shall be included in #
+# all copies or substantial portions of the Software.                        #
+#                                                                            #
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR #
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,   #
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL    #
+# THE ABOVE COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER      #
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING    #
+# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER        #
+# DEALINGS IN THE SOFTWARE.                                                  #
+#                                                                            #
+# Except as contained in this notice, the name(s) of the above copyright     #
+# holders shall not be used in advertising or otherwise to promote the sale, #
+# use or other dealings in this Software without prior written               #
+# authorization.                                                             #
+##############################################################################
+#
+# Author: Thomas E. Dickey, 2006-on
+
+LANG=C;		export LANG
+LANGUAGE=C;	export LANGUAGE
+LC_ALL=C;	export LC_ALL
+LC_CTYPE=C;	export LC_CTYPE
+
+prefix="/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application"
+exec_prefix="${prefix}"
+
+bindir="${exec_prefix}/bin"
+includedir="${prefix}/include"
+libdir="${exec_prefix}/lib"
+datarootdir="${prefix}/share"
+datadir="${datarootdir}"
+mandir="${datarootdir}/man"
+
+THIS="ncursesw"
+TINFO_LIB="tinfow"
+RPATH_LIST="${libdir}"
+
+includesubdir="${prefix}/include/${THIS}"
+
+# Ensure that RPATH_LIST contains only absolute pathnames, if it is nonempty.
+# We cannot filter it out within the build-process since the variable is used
+# in some special cases of installation using a relative path.
+if [ -n "$RPATH_LIST" ]
+then
+	save_IFS="$IFS"
+	IFS=':'
+	filtered=
+	for item in $RPATH_LIST
+	do
+		case "$item" in
+		./*|../*|*/..|*/../*)
+			;;
+		*)
+			[ -n "$filtered" ] && filtered="${filtered}:"
+			filtered="${filtered}${item}"
+			;;
+		esac
+	done
+	IFS="$save_IFS"
+	# if the result is empty, there is little we can do to fix it
+	RPATH_LIST="$filtered"
+fi
+
+# with --disable-overwrite, we installed into a subdirectory, but transformed
+# the headers to include like this:
+#	<ncursesw/curses.h>
+if [ xno = xno ]; then
+	case $includedir in
+	$prefix/include/ncursesw)
+		includedir=`echo "$includedir" | sed -e 's,/[^/]*$,,'`
+		;;
+	esac
+fi
+
+LIBS=""
+if [ "tinfo" = "ncurses" ]; then
+	LIBS="-l${THIS} $LIBS"
+else
+	LIBS="-l${THIS} -l${TINFO_LIB} $LIBS"
+fi
+
+# Ignore -L options which do not correspond to an actual directory, or which
+# are standard library directories (i.e., the linker is supposed to search
+# those directories).
+#
+# There is no portable way to find the list of standard library directories.
+# Require a POSIX shell anyway, to keep this simple.
+lib_flags=
+for opt in -L$libdir -Wl,-pie -Wl,-headerpad_max_install_names -Wl,-dead_strip_dylibs -Wl,-rpath,/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/lib -L/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/lib -Wl,-search_paths_first  $LIBS
+do
+	case $opt in
+	-specs*) # ignore linker specs-files which were used to build library
+		continue
+		;;
+	-Wl,-z,*) # ignore flags used to manipulate shared image
+		continue
+		;;
+	-Wl,--dynamic-linker*) # ignore ELF interpreter
+		continue
+		;;
+	-Wl,--as-needed|-Wl,--build-id=*|-Wl,-dT,*|-Wl,-T,*)
+		continue
+		;;
+	-L*)
+		lib_check=`echo "x$opt" | sed -e 's/^.-L//'`
+		[ -d "$lib_check" ] || continue
+		case "$lib_check" in
+		$HOME/lib|/usr/lib) # skip standard libdir
+			if [ "$lib_check" = "$libdir" ]
+			then
+				lib_first=yes
+				IFS_save="$IFS"
+				IFS='|'
+				LIBDIRS="$HOME/lib|/usr/lib"
+				for lib_check in $LIBDIRS
+				do
+					if [ -d "$lib_check" ]
+					then
+						if [ "$lib_check" != "$libdir" ]
+						then
+							lib_first=no
+						fi
+						break
+					fi
+				done
+				IFS="$IFS_save"
+				[ $lib_first = yes ] && continue
+				found=no
+				for check in $lib_flags
+				do
+					if [ "x$check" = "x$opt" ]
+					then
+						found=yes
+						break
+					fi
+				done
+				[ $found = yes ] && continue
+				:
+			else
+				continue
+			fi
+			;;
+		*)
+			found=no
+			for check in $lib_flags
+			do
+				if [ "x$check" = "x$opt" ]
+				then
+					found=yes
+					break
+				fi
+			done
+			[ $found = yes ] && continue
+			;;
+		esac
+		;;
+	esac
+	lib_flags="$lib_flags $opt"
+done
+
+[ $# = 0 ] && exec /bin/sh "$0" --error
+
+while [ $# -gt 0 ]; do
+	case "$1" in
+	# basic configuration
+	--prefix)
+		echo "$prefix"
+		;;
+	--exec-prefix)
+		echo "$exec_prefix"
+		;;
+	# compile/link
+	--cflags)
+		INCS=" -D_DARWIN_C_SOURCE -DNCURSES_WIDECHAR"
+		if [ "xno" = xno ]; then
+			INCS="$INCS -I${includesubdir}"
+		fi
+		if [ "${includedir}" != /usr/include ]; then
+			INCS="$INCS -I${includedir}"
+		fi
+		sed -e 's,^[ ]*,,' -e 's, [ ]*, ,g' -e 's,[ ]*$,,' <<-ENDECHO
+			$INCS
+ENDECHO
+		;;
+	--libs)
+		OPTS=
+		for opt in $lib_flags
+		do
+			[ -n "$OPTS" ] && OPTS="$OPTS "
+			OPTS="${OPTS}${opt}"
+		done
+		printf '%s\n' "$OPTS"
+		;;
+	--libs-only-L)
+		OPTS=
+		for opt in $lib_flags
+		do
+			case "x$opt" in
+			x-L*)
+				[ -n "$OPTS" ] && OPTS="$OPTS "
+				OPTS="${OPTS}${opt}"
+				;;
+			esac
+		done
+		printf '%s\n' "$OPTS"
+		;;
+	--libs-only-l)
+		OPTS=
+		for opt in $lib_flags
+		do
+			case "x$opt" in
+			x-l*)
+				[ -n "$OPTS" ] && OPTS="$OPTS "
+				OPTS="${OPTS}${opt}"
+				;;
+			esac
+		done
+		printf '%s\n' "$OPTS"
+		;;
+	--libs-only-other)
+		OPTS=
+		for opt in $lib_flags
+		do
+			case "x$opt" in
+			x-[lL]*)
+				;;
+			*)
+				[ -n "$OPTS" ] && OPTS="$OPTS "
+				OPTS="${OPTS}${opt}"
+				;;
+			esac
+		done
+		printf '%s\n' "$OPTS"
+		;;
+	# identification
+	--version)
+		echo "6.4.20221231"
+		;;
+	--abi-version)
+		echo "6"
+		;;
+	--mouse-version)
+		echo "2"
+		;;
+	# locations
+	--bindir)
+		echo "${bindir}"
+		;;
+	--datadir)
+		echo "${datadir}"
+		;;
+	--includedir)
+		INCS=
+		if [ "xno" = xno ]; then
+			INCS="${includesubdir}"
+		elif [ "${includedir}" != /usr/include ]; then
+			INCS="${includedir}"
+		fi
+		echo "$INCS"
+		;;
+	--libdir)
+		echo "${libdir}"
+		;;
+	--mandir)
+		echo "${mandir}"
+		;;
+	--terminfo)
+		echo "/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/share/terminfo"
+		;;
+	--terminfo-dirs)
+		echo "/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/share/terminfo"
+		;;
+	--termpath)
+		echo "/etc/termcap:/usr/share/misc/termcap"
+		;;
+	# general info
+	--help)
+		cat <<ENDHELP
+Usage: `basename "$0"` [options]
+
+Options:
+  --prefix           echos the package-prefix of ${THIS}
+  --exec-prefix      echos the executable-prefix of ${THIS}
+
+  --cflags           echos the C compiler flags needed to compile with ${THIS}
+  --libs             echos the libraries needed to link with ${THIS}
+
+  --libs-only-L      echos -L linker options (search path) for ${THIS}
+  --libs-only-l      echos -l linker options (libraries) for ${THIS}
+  --libs-only-other  echos linker options other than -L/-l
+
+  --version          echos the release+patchdate version of ${THIS}
+  --abi-version      echos the ABI version of ${THIS}
+  --mouse-version    echos the mouse-interface version of ${THIS}
+
+  --bindir           echos the directory containing ${THIS} programs
+  --datadir          echos the directory containing ${THIS} data
+  --includedir       echos the directory containing ${THIS} header files
+  --libdir           echos the directory containing ${THIS} libraries
+  --mandir           echos the directory containing ${THIS} manpages
+  --terminfo         echos the \$TERMINFO terminfo database path
+  --terminfo-dirs    echos the \$TERMINFO_DIRS directory list
+  --termpath         echos the \$TERMPATH termcap list
+
+  --help             prints this message
+ENDHELP
+		;;
+	--error|*)
+		/bin/sh "$0" --help 1>&2
+		exit 1
+		;;
+	esac
+	shift
+done
+# vi:ts=4 sw=4
+# vile:shmode

ocr-application/bin/normalizer

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from charset_normalizer.cli import cli_detect
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli_detect())

ocr-application/bin/numpy-config

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from numpy._configtool import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

ocr-application/bin/openai

@@ -0,0 +1,8 @@
+#!/Users/shashankreddykandimalla/Desktop/ocr-application/ocr-application/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from openai.cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())