using go-flags to manage command line input.

Readme.md

@@ -10,7 +10,7 @@ Search for words similar to "death" in Hemingway's "The Old Man and the Sea" wit
 
 ```bash
 curl -s 'https://gutenberg.ca/ebooks/hemingwaye-oldmanandthesea/hemingwaye-oldmanandthesea-00-t.txt' \
-    | w2vgrep -C 2 -n -threshold 0.55 death
+    | w2vgrep -C 2 -n --threshold=0.55 death
 ```
 
 Output:
@@ -86,16 +86,17 @@ Basic usage:
 If no file is specified, w2vgrep reads from standard input.
 
 ### Command-line Options
-
-- `-model_path`: Path to the Word2Vec model file ('models/glove/glove.6B.300d.bin'). Overrides config file.
-- `-threshold`: Similarity threshold for matching (default: 0.7)
-- `-A`: Number of lines to display after a match
-- `-B`: Number of lines to display before a match
-- `-C`: Number of lines to display before and after a match
-- `-n`: Print line numbers
-- `-o`: Print only matching word
-- `-l`: Print only matched lines
-- `-i`: Case insensitive matching
+```
+-m, --model_path=     Path to the Word2Vec model file. Overrides config file
+-t, --threshold=      Similarity threshold for matching (default: 0.7)
+-A, --before-context= Number of lines before matching line
+-B, --after-context=  Number of lines after matching line
+-C, --context=        Number of lines before and after matching line
+-n, --line-number     Print line numbers
+-i, --ignore-case     Ignore case. 
+-o, --only-matching   Output only matching words
+-l, --only-lines      Output only matched lines without similarity scores
+```
 
 ## Configuration
 
@@ -119,7 +120,7 @@ curl -s 'https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.fr.300.vec.gz'
 
 # use it like so:
 # curl -s 'https://www.gutenberg.org/cache/epub/17989/pg17989.txt' \
-#    | w2vgrep -C 2 -n -threshold 0.55 \
+#    | w2vgrep -C 2 -n -t 0.55 \
 #           -model_path model_processing_utils/cc.fr.300.bin 'château'
 ```
 

go.mod

@@ -2,6 +2,12 @@ module w2vgrep
 
 go 1.22.5
 
-require github.com/clipperhouse/uax29 v1.13.0
+require (
+	github.com/clipperhouse/uax29 v1.13.0
+	github.com/jessevdk/go-flags v1.6.1
+)
 
-require golang.org/x/text v0.16.0 // indirect
+require (
+	golang.org/x/sys v0.21.0 // indirect
+	golang.org/x/text v0.16.0 // indirect
+)

go.sum

@@ -1,4 +1,8 @@
 github.com/clipperhouse/uax29 v1.13.0 h1:5q58IRS9gBATd+NtnPXAmul5PLTGFeQ3lv0C51zhIEk=
 github.com/clipperhouse/uax29 v1.13.0/go.mod h1:paNABhygWmmjkg0ROxKQoenJAX4dM9AS8biVkXmAK0c=
+github.com/jessevdk/go-flags v1.6.1 h1:Cvu5U8UGrLay1rZfv/zP7iLpSHGUZ/Ou68T0iX1bBK4=
+github.com/jessevdk/go-flags v1.6.1/go.mod h1:Mk8T1hIAWpOiJiHa9rJASDK2UGWji0EuPGBnNLMooyc=
+golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws=
+golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
 golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=

w2vgrep.go

@@ -1,44 +1,59 @@
 package main
 
 import (
-	"flag"
 	"fmt"
 	"os"
 
 	"w2vgrep/modules/config"
 	"w2vgrep/modules/model"
 	"w2vgrep/modules/processor"
 	"w2vgrep/modules/similarity"
+
+	"github.com/jessevdk/go-flags"
 )
 
+// Options defines the command-line options
+type Options struct {
+	ModelPath           string  `short:"m" long:"model_path" description:"Path to the Word2Vec model file"`
+	SimilarityThreshold float64 `short:"t" long:"threshold" default:"0.7" description:"Similarity threshold for matching"`
+	ContextBefore       int     `short:"A" long:"before-context" description:"Number of lines before matching line"`
+	ContextAfter        int     `short:"B" long:"after-context" description:"Number of lines after matching line"`
+	ContextBoth         int     `short:"C" long:"context" description:"Number of lines before and after matching line"`
+	PrintLineNumbers    bool    `short:"n" long:"line-number" description:"Print line numbers"`
+	IgnoreCase          bool    `short:"i" long:"ignore-case" description:"Ignore case. Note: word2vec is case-sensitive. Ignoring case may lead to unexpected results"`
+	OutputOnlyMatching  bool    `short:"o" long:"only-matching" description:"Output only matching words"`
+	OutputOnlyLines     bool    `short:"l" long:"only-lines" description:"Output only matched lines without similarity scores"`
+}
+
 func main() {
-	modelPath := flag.String("model_path", "", "Path to the Word2Vec model file")
-	similarityThreshold := flag.Float64("threshold", 0.7, "Similarity threshold for matching")
-	contextBefore := flag.Int("A", 0, "Number of lines before matching line")
-	contextAfter := flag.Int("B", 0, "Number of lines after matching line")
-	contextBoth := flag.Int("C", 0, "Number of lines before and after matching line")
-	printLineNumbers := flag.Bool("n", false, "Print line numbers")
-	ignoreCase := flag.Bool("i", false, "Ignore case. Note: word2vec is case-sensitive. Ignoring case may lead to unexpected results")
-	outputOnlyMatching := flag.Bool("o", false, "Output only matching words")
-	outputOnlyLines := flag.Bool("l", false, "Output only matched lines without similarity scores")
-
-	flag.Parse()
-
-	if *contextBoth > 0 {
-		*contextBefore = *contextBoth
-		*contextAfter = *contextBoth
+	var opts Options
+	var parser = flags.NewParser(&opts, flags.Default)
+	parser.Usage = "[OPTIONS] QUERY [FILE]"
+
+	args, err := parser.Parse()
+	if err != nil {
+		if flagsErr, ok := err.(*flags.Error); ok && flagsErr.Type == flags.ErrHelp {
+			os.Exit(0)
+		} else {
+			fmt.Fprintf(os.Stderr, "Error: %v\n", err)
+			parser.WriteHelp(os.Stderr)
+			os.Exit(1)
+		}
 	}
 
-	args := flag.Args()
 	if len(args) < 1 {
 		fmt.Fprintln(os.Stderr, "Error: query is required")
-		flag.PrintDefaults()
+		parser.WriteHelp(os.Stderr)
 		os.Exit(1)
 	}
 
+	if opts.ContextBoth > 0 {
+		opts.ContextBefore = opts.ContextBoth
+		opts.ContextAfter = opts.ContextBoth
+	}
+
 	query := args[0]
 	var input *os.File
-	var err error
 
 	if len(args) > 1 {
 		input, err = os.Open(args[1])
@@ -61,29 +76,28 @@ func main() {
 		}
 		fmt.Fprintf(os.Stderr, "Using configuration file: %s\n", configPath)
 
-		if *modelPath == "" {
-			*modelPath = conf.ModelPath
+		if opts.ModelPath == "" {
+			opts.ModelPath = conf.ModelPath
 		}
 	}
 
-	if *modelPath == "" {
-		fmt.Fprintln(os.Stderr, "Error: Model path is required. Please provide it via config file or -model_path flag.")
-		flag.PrintDefaults()
+	if opts.ModelPath == "" {
+		fmt.Fprintln(os.Stderr, "Error: Model path is required. Please provide it via config file or -m/--model_path flag.")
+		parser.WriteHelp(os.Stderr)
 		os.Exit(1)
 	}
 
 	var w2vModel model.VectorModel
 	var similarityCache similarity.SimilarityCache
 
-	w2vModel, err = model.LoadVectorModel(*modelPath)
+	w2vModel, err = model.LoadVectorModel(opts.ModelPath)
 	if err != nil {
 		fmt.Fprintf(os.Stderr, "Error loading full model: %v\n", err)
 		os.Exit(1)
 	}
 	similarityCache = similarity.NewSimilarityCache()
 
-	// Dereference the pointers when passing to ProcessLineByLine
-	processor.ProcessLineByLine(query, w2vModel, similarityCache, *similarityThreshold,
-		*contextBefore, *contextAfter, input, *printLineNumbers, *ignoreCase,
-		*outputOnlyMatching, *outputOnlyLines)
+	processor.ProcessLineByLine(query, w2vModel, similarityCache, opts.SimilarityThreshold,
+		opts.ContextBefore, opts.ContextAfter, input, opts.PrintLineNumbers, opts.IgnoreCase,
+		opts.OutputOnlyMatching, opts.OutputOnlyLines)
 }