universal_document_processor 1.0.1 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c33ef9db6830ddb62e98966d0bf3dd85106833e260303651df297bb3d46b9529
-  data.tar.gz: 280fa75bf3d842fc1af11dd95ca49e0526ed22512b5732aed0a7c25d4a57a7d9
+  metadata.gz: '06539a78d5cc253518f84b242dd7a8dcb71ce575614d7e8853bb9de70b031f75'
+  data.tar.gz: c58e957dfe6940c0cb16fb4c50f9ce0ee69aa7cf9a7587b2496a80da78bbdda8
 SHA512:
-  metadata.gz: 01d6c5129dc7ec1a7911a77ba69b8dbafd32bd9397e0374175a4cf09cf24f8c06225a0bc927b1e3bba8250e3d1e93d40bbbc1dbf3aa1a6ff0fbc92cb7f5f24a4
-  data.tar.gz: b445b8d773e2865e6e2c5593c123cc7d0da580d4d16822e4b9e45c851568f077f4c949d921f2f602c4ed3ff941ccf8a1d002eb14401c554b0f8355dc293bff62
+  metadata.gz: 81940e620b3dcff668493ae459e1287161ccbc56b8677acab3477913685d4f68580f0d4062ae0e777e83a000aa58a42619f3a96d0f19b2146e38fa2c3418587a
+  data.tar.gz: 61b98794dc95f0489a806d1dbb31b172f75570ac2fa140d0ff334347f58afdbfab370ffd72b003b948b7a4ec80656e6f29b196ca833e0b219b41316ebb729843

data/CHANGELOG.md

@@ -7,6 +7,26 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.2.0] - 2024-01-15
+### Added
+- **TSV (Tab-Separated Values) File Support**: Complete built-in TSV processing capabilities
+  - Native TSV parsing using Ruby CSV library with tab delimiter
+  - Text extraction with proper formatting
+  - Comprehensive metadata detection (format, delimiter, encoding)
+  - Table structure analysis and header detection
+  - Statistical analysis and data validation
+  - Format conversions: TSV ↔ CSV, TSV → JSON
+  - Cross-format compatibility with existing CSV and Excel features
+  - New `to_tsv()` method for converting other formats to TSV
+  - Enhanced file detector with TSV MIME type mapping
+  - Full integration with existing Document class API
+
+### Enhanced
+- **ExcelProcessor**: Extended to handle TSV files alongside CSV and Excel formats
+- **File Detection**: Added TSV MIME type support (`text/tab-separated-values`)
+- **Document Class**: Added `to_tsv()` method and TSV format support
+- **Supported Formats**: Updated to include TSV in format list
+
 ## [1.0.1] - 2025-06-23
 
 ### Fixed

data/README.md

@@ -16,7 +16,7 @@ A comprehensive Ruby gem that provides unified document processing capabilities
 
 ### **Supported File Formats**
 - **📄 Documents**: PDF, DOC, DOCX, RTF
-- **📊 Spreadsheets**: XLS, XLSX, CSV
+- **📊 Spreadsheets**: XLS, XLSX, CSV, TSV
 - **📺 Presentations**: PPT, PPTX
 - **🖼️ Images**: JPG, PNG, GIF, BMP, TIFF
 - **📁 Archives**: ZIP, RAR, 7Z
@@ -236,6 +236,58 @@ tables.each_with_index do |table, index|
 end
 ```
 
+### Processing TSV (Tab-Separated Values) Files
+
+```ruby
+# Process TSV files with built-in support
+result = UniversalDocumentProcessor.process('data.tsv')
+
+# TSV-specific metadata
+metadata = result[:metadata]
+puts "Format: #{metadata[:format]}"        # => "tsv"
+puts "Delimiter: #{metadata[:delimiter]}"  # => "tab"
+puts "Rows: #{metadata[:total_rows]}"
+puts "Columns: #{metadata[:total_columns]}"
+puts "Has headers: #{metadata[:has_headers]}"
+
+# Extract structured data
+tables = result[:tables]
+table = tables.first
+puts "Headers: #{table[:headers].join(', ')}"
+puts "Sample row: #{table[:data][1].join(' | ')}"
+
+# Format conversions
+document = UniversalDocumentProcessor::Document.new('data.tsv')
+
+# Convert TSV to CSV
+csv_output = document.to_csv
+puts "CSV conversion: #{csv_output.length} characters"
+
+# Convert TSV to JSON
+json_output = document.to_json
+puts "JSON conversion: #{json_output.length} characters"
+
+# Convert CSV to TSV
+csv_document = UniversalDocumentProcessor::Document.new('data.csv')
+tsv_output = csv_document.to_tsv
+puts "TSV conversion: #{tsv_output.length} characters"
+
+# Statistical analysis
+stats = document.extract_statistics
+sheet_stats = stats['Sheet1']
+puts "Total cells: #{sheet_stats[:total_cells]}"
+puts "Numeric cells: #{sheet_stats[:numeric_cells]}"
+puts "Text cells: #{sheet_stats[:text_cells]}"
+puts "Average value: #{sheet_stats[:average_value]}"
+
+# Data validation
+validation = document.validate_data
+sheet_validation = validation['Sheet1']
+puts "Data quality score: #{sheet_validation[:data_quality_score]}%"
+puts "Empty rows: #{sheet_validation[:empty_rows]}"
+puts "Duplicate rows: #{sheet_validation[:duplicate_rows]}"
+```
+
 ### Processing Word Documents
 
 ```ruby

data/lib/universal_document_processor/document.rb

@@ -48,6 +48,42 @@ module UniversalDocumentProcessor
       []
     end
 
+    def extract_statistics
+      processor.respond_to?(:extract_statistics) ? processor.extract_statistics : {}
+    rescue => e
+      {}
+    end
+
+    def validate_data
+      processor.respond_to?(:validate_data) ? processor.validate_data : {}
+    rescue => e
+      {}
+    end
+
+    def extract_formulas
+      processor.respond_to?(:extract_formulas) ? processor.extract_formulas : []
+    rescue => e
+      []
+    end
+
+    def to_json
+      processor.respond_to?(:to_json) ? processor.to_json : process.to_json
+    rescue => e
+      process.to_json
+    end
+
+    def to_csv(sheet_name = nil)
+      processor.respond_to?(:to_csv) ? processor.to_csv(sheet_name) : ""
+    rescue => e
+      ""
+    end
+
+    def to_tsv(sheet_name = nil)
+      processor.respond_to?(:to_tsv) ? processor.to_tsv(sheet_name) : ""
+    rescue => e
+      ""
+    end
+
     def convert_to(target_format)
       case target_format.to_sym
       when :pdf
@@ -64,7 +100,7 @@ module UniversalDocumentProcessor
     end
 
     def supported_formats
-      %w[pdf docx doc xlsx xls pptx ppt txt rtf html xml csv jpg jpeg png gif bmp tiff zip rar 7z]
+      %w[pdf docx doc xlsx xls pptx ppt txt rtf html xml csv tsv jpg jpeg png gif bmp tiff zip rar 7z]
     end
 
     def supported?
@@ -139,11 +175,11 @@ module UniversalDocumentProcessor
       case @content_type
       when /pdf/
         Processors::PdfProcessor.new(@file_path, @options)
-      when /word/, /document/
+      when /wordprocessingml/, /msword/
         Processors::WordProcessor.new(@file_path, @options)
-      when /excel/, /spreadsheet/
+      when /spreadsheetml/, /ms-excel/, /csv/, /tab-separated/
         Processors::ExcelProcessor.new(@file_path, @options)
-      when /powerpoint/, /presentation/
+      when /presentationml/, /ms-powerpoint/
         Processors::PowerpointProcessor.new(@file_path, @options)
       when /image/
         Processors::ImageProcessor.new(@file_path, @options)