searchindocs.ps1

# Set error reporting

Set-StrictMode -Version latest

# Check if the required arguments are provided

if ($args.Count -ne 2) {

	Write-Host "Usage: searchindocs.ps1 <SearchedString> <SearchPath>"

	exit

}

# Retrieve command line arguments

$findtext = $args[0]

$path = $args[1]

# COM object for Word

$application = New-Object -ComObject Word.Application

$application.Visible = $false

$charactersAround = 30

$results = @()

Function GetStringMatch {

	# Get all Word document files in the specified directory and subdirectories

	$files = Get-ChildItem $path -Include *.docx, *.doc, *.odt, *.rtf -Recurse | Where-Object { -not $_.PSIsContainer }

	# Loop through each Word document

	foreach ($file in $files) {

		$document = $application.Documents.Open($file.FullName, $true, $false)

		$range = $document.Content

		# Skip password protected documents
		
		if (!$document.HasPassword) {

			# Search for the word and extract surrounding text

			if ($range.Text -match ".{$charactersAround}$findtext.{$charactersAround}") {

				Write-Host "File: $($file.FullName)"

				Write-Host "Match: $findtext"

				Write-Host "TextAround: $($Matches[0])"

				Write-Host

			}

		}

		$document.Close()

	}

}

GetStringMatch

searchindocs.sh

#!/bin/bash

# Check if the required arguments are provided
if [ "$#" -ne 2 ]; then
    echo "Usage: searchindocs.sh <SearchedString> <SearchPath>"
    exit 1
fi

findtext="$1"
path="$2"
charactersAround=30

# Loop through each ODT document
while IFS= read -r -d '' file; do
    # Extract text from the ODT document and search for the string
    text=$(libreoffice --headless --cat "$file")
    if [[ $text =~ .{${charactersAround}}$findtext.{${charactersAround}} ]]; then
        echo "File: $file"
        echo "Match: $findtext"
        echo "TextAround: ${BASH_REMATCH[0]}"
        echo
    fi
done < <(find "$path" -type f -name "*.odt" -print0)