add exif extraction, virtual folders

Author: bbedward

README.md

@@ -16,14 +16,16 @@
 
 # dsearch
 
-A configurable filesystem search service powered by [bleve](https://github.com/blevesearch/bleve) for GNU/Linux.
+A configurable filesystem search service powered by [bleve](https://github.com/blevesearch/bleve) for Unix-based operating systems.
 
 ## Features
 
 - **Indexing** - Indexes all files in specified paths
 - **Configuration** - Configure exclusions, depth, etc.
 - **Fuzzy search** - Typo-tolerant search queries
 - **Text content extraction** - Optionally extracts and indexes content from text-based files
+- **EXIF metadata** - Extracts and indexes EXIF data from image files for advanced search
+- **Virtual folders** - Search within specific directories
 - **Concurrent indexing** - Multi-worker parallel indexing for fast performance
 - **Real-time updates** - File watcher for incremental index updates
 
@@ -62,6 +64,32 @@ dsearch search "typo" --fuzzy
 dsearch search "*" --sort mtime --desc
 # Scores content higher than filenames
 dsearch search --field body mountain
+
+# Virtual folder search
+dsearch search "*" --folder /home/user/Pictures
+
+# EXIF metadata search and filtering
+dsearch search "*" --ext .jpg --exif-make Canon
+dsearch search "*" --exif-model "Canon EOS 5D"
+dsearch search "*" --folder /home/user/Photos --exif-make Nikon
+
+# Sort photos by date taken (newest first)
+dsearch search "*" --ext .jpg --sort exif_date --desc
+
+# Find photos by ISO range (low-light shots)
+dsearch search "*" --exif-min-iso 1600 --exif-max-iso 6400
+
+# Find portrait shots (focal length range)
+dsearch search "*" --exif-min-focal-len 50 --exif-max-focal-len 135
+
+# Find wide aperture shots (shallow depth of field)
+dsearch search "*" --exif-min-aperture 1.4 --exif-max-aperture 2.8
+
+# Photos taken in date range
+dsearch search "*" --exif-date-after "2024-06-01T00:00:00Z" --exif-date-before "2024-08-31T23:59:59Z"
+
+# GPS location filtering (bounding box)
+dsearch search "*" --exif-lat-min 40.0 --exif-lat-max 41.0 --exif-lon-min -74.0 --exif-lon-max -73.0
 ```
 
 For all options:

cmd/dsearch/main.go

@@ -34,15 +34,30 @@ var (
 	httpOnly      bool
 	socketOnly    bool
 
-	searchLimit    int
-	searchField    string
-	searchExt      string
-	searchFuzzy    bool
-	searchSort     string
-	searchSortDesc bool
-	searchMinSize  int64
-	searchMaxSize  int64
-	searchJSON     bool
+	searchLimit           int
+	searchField           string
+	searchExt             string
+	searchFuzzy           bool
+	searchSort            string
+	searchSortDesc        bool
+	searchMinSize         int64
+	searchMaxSize         int64
+	searchJSON            bool
+	searchFolder          string
+	searchExifMake        string
+	searchExifModel       string
+	searchExifDateAfter   string
+	searchExifDateBefore  string
+	searchExifMinISO      int
+	searchExifMaxISO      int
+	searchExifMinAp       float64
+	searchExifMaxAp       float64
+	searchExifMinFocalLen float64
+	searchExifMaxFocalLen float64
+	searchExifLatMin      float64
+	searchExifLatMax      float64
+	searchExifLonMin      float64
+	searchExifLonMax      float64
 )
 
 var rootCmd = &cobra.Command{
@@ -138,11 +153,26 @@ func init() {
 	searchCmd.Flags().StringVarP(&searchField, "field", "f", "", "search specific field (filename, body, title)")
 	searchCmd.Flags().StringVarP(&searchExt, "ext", "e", "", "filter by file extension (e.g., .jpg)")
 	searchCmd.Flags().BoolVar(&searchFuzzy, "fuzzy", false, "enable fuzzy matching for typos")
-	searchCmd.Flags().StringVar(&searchSort, "sort", "score", "sort by: score, mtime, size, filename")
+	searchCmd.Flags().StringVar(&searchSort, "sort", "score", "sort by: score, mtime, size, filename, exif_date, iso, focal_length, aperture")
 	searchCmd.Flags().BoolVar(&searchSortDesc, "desc", true, "sort descending")
 	searchCmd.Flags().Int64Var(&searchMinSize, "min-size", 0, "minimum file size in bytes")
 	searchCmd.Flags().Int64Var(&searchMaxSize, "max-size", 0, "maximum file size in bytes")
 	searchCmd.Flags().BoolVar(&searchJSON, "json", false, "output results in JSON format")
+	searchCmd.Flags().StringVar(&searchFolder, "folder", "", "filter by folder path (e.g., /home/user/Pictures)")
+	searchCmd.Flags().StringVar(&searchExifMake, "exif-make", "", "filter by camera make (e.g., Canon)")
+	searchCmd.Flags().StringVar(&searchExifModel, "exif-model", "", "filter by camera model (e.g., Canon EOS 5D)")
+	searchCmd.Flags().StringVar(&searchExifDateAfter, "exif-date-after", "", "photos taken after date (RFC3339 or EXIF format)")
+	searchCmd.Flags().StringVar(&searchExifDateBefore, "exif-date-before", "", "photos taken before date (RFC3339 or EXIF format)")
+	searchCmd.Flags().IntVar(&searchExifMinISO, "exif-min-iso", 0, "minimum ISO value")
+	searchCmd.Flags().IntVar(&searchExifMaxISO, "exif-max-iso", 0, "maximum ISO value")
+	searchCmd.Flags().Float64Var(&searchExifMinAp, "exif-min-aperture", 0, "minimum aperture (f-number)")
+	searchCmd.Flags().Float64Var(&searchExifMaxAp, "exif-max-aperture", 0, "maximum aperture (f-number)")
+	searchCmd.Flags().Float64Var(&searchExifMinFocalLen, "exif-min-focal-len", 0, "minimum focal length in mm")
+	searchCmd.Flags().Float64Var(&searchExifMaxFocalLen, "exif-max-focal-len", 0, "maximum focal length in mm")
+	searchCmd.Flags().Float64Var(&searchExifLatMin, "exif-lat-min", 0, "minimum GPS latitude")
+	searchCmd.Flags().Float64Var(&searchExifLatMax, "exif-lat-max", 0, "maximum GPS latitude")
+	searchCmd.Flags().Float64Var(&searchExifLonMin, "exif-lon-min", 0, "minimum GPS longitude")
+	searchCmd.Flags().Float64Var(&searchExifLonMax, "exif-lon-max", 0, "maximum GPS longitude")
 
 	indexCmd.AddCommand(indexGenerateCmd)
 	indexCmd.AddCommand(indexSyncCmd)
@@ -304,15 +334,30 @@ func runSearch(cmd *cobra.Command, args []string) error {
 	}
 
 	clientOpts := &client.SearchOptions{
-		Query:     query,
-		Limit:     limit,
-		Field:     searchField,
-		Extension: searchExt,
-		Fuzzy:     searchFuzzy,
-		SortBy:    searchSort,
-		SortDesc:  searchSortDesc,
-		MinSize:   searchMinSize,
-		MaxSize:   searchMaxSize,
+		Query:           query,
+		Limit:           limit,
+		Field:           searchField,
+		Extension:       searchExt,
+		Fuzzy:           searchFuzzy,
+		SortBy:          searchSort,
+		SortDesc:        searchSortDesc,
+		MinSize:         searchMinSize,
+		MaxSize:         searchMaxSize,
+		Folder:          searchFolder,
+		ExifMake:        searchExifMake,
+		ExifModel:       searchExifModel,
+		ExifDateAfter:   searchExifDateAfter,
+		ExifDateBefore:  searchExifDateBefore,
+		ExifMinISO:      searchExifMinISO,
+		ExifMaxISO:      searchExifMaxISO,
+		ExifMinAperture: searchExifMinAp,
+		ExifMaxAperture: searchExifMaxAp,
+		ExifMinFocalLen: searchExifMinFocalLen,
+		ExifMaxFocalLen: searchExifMaxFocalLen,
+		ExifLatMin:      searchExifLatMin,
+		ExifLatMax:      searchExifLatMax,
+		ExifLonMin:      searchExifLonMin,
+		ExifLonMax:      searchExifLonMax,
 	}
 
 	result, err := client.SearchWithOptions(clientOpts)
@@ -348,15 +393,30 @@ func runSearch(cmd *cobra.Command, args []string) error {
 	}
 
 	indexerOpts := &indexer.SearchOptions{
-		Query:     query,
-		Limit:     limit,
-		Field:     searchField,
-		Extension: searchExt,
-		Fuzzy:     searchFuzzy,
-		SortBy:    searchSort,
-		SortDesc:  searchSortDesc,
-		MinSize:   searchMinSize,
-		MaxSize:   searchMaxSize,
+		Query:           query,
+		Limit:           limit,
+		Field:           searchField,
+		Extension:       searchExt,
+		Fuzzy:           searchFuzzy,
+		SortBy:          searchSort,
+		SortDesc:        searchSortDesc,
+		MinSize:         searchMinSize,
+		MaxSize:         searchMaxSize,
+		Folder:          searchFolder,
+		ExifMake:        searchExifMake,
+		ExifModel:       searchExifModel,
+		ExifDateAfter:   searchExifDateAfter,
+		ExifDateBefore:  searchExifDateBefore,
+		ExifMinISO:      searchExifMinISO,
+		ExifMaxISO:      searchExifMaxISO,
+		ExifMinAperture: searchExifMinAp,
+		ExifMaxAperture: searchExifMaxAp,
+		ExifMinFocalLen: searchExifMinFocalLen,
+		ExifMaxFocalLen: searchExifMaxFocalLen,
+		ExifLatMin:      searchExifLatMin,
+		ExifLatMax:      searchExifLatMax,
+		ExifLonMin:      searchExifLonMin,
+		ExifLonMax:      searchExifLonMax,
 	}
 
 	result, err = idx.SearchWithOptions(indexerOpts)

config.example.toml

@@ -36,6 +36,7 @@ text_extensions = [
 path = "/home/brandon"
 max_depth = 6  # Default depth for home directory
 exclude_hidden = true
+extract_exif = true  # Extract EXIF metadata from images
 exclude_dirs = [
     "node_modules", "bower_components", "__pycache__", "site-packages",
     "venv", ".venv", "target", "dist", "build", "vendor", ".cache"
@@ -45,6 +46,7 @@ exclude_dirs = [
 path = "/home/brandon/repos"
 max_depth = 6  # Go deeper for repos directory
 exclude_hidden = true
+extract_exif = false  # Skip EXIF extraction for code repos
 exclude_dirs = [
     "node_modules", "bower_components", "__pycache__", "site-packages",
     "venv", ".venv", "target", "dist", "build", "vendor", ".cache",
@@ -55,4 +57,5 @@ exclude_dirs = [
 path = "/home/brandon/Documents"
 max_depth = 0  # Unlimited depth for Documents
 exclude_hidden = false  # Include hidden files in Documents
+extract_exif = true  # Extract EXIF metadata from images
 exclude_dirs = []

go.mod

@@ -10,6 +10,7 @@ require (
 	github.com/danielgtaylor/huma/v2 v2.34.1
 	github.com/fsnotify/fsnotify v1.9.0
 	github.com/go-chi/chi/v5 v5.2.3
+	github.com/rwcarlsen/goexif v0.0.0-20190401172101-9e8deecbddbd
 	github.com/spf13/cobra v1.10.1
 )
 

go.sum

@@ -99,6 +99,8 @@ github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJ
 github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
 github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/rwcarlsen/goexif v0.0.0-20190401172101-9e8deecbddbd h1:CmH9+J6ZSsIjUK3dcGsnCnO41eRBOnY12zwkn5qVwgc=
+github.com/rwcarlsen/goexif v0.0.0-20190401172101-9e8deecbddbd/go.mod h1:hPqNNc0+uJM6H+SuU8sEs5K5IQeKccPqeSjfgcKGgPk=
 github.com/spf13/cobra v1.10.1 h1:lJeBwCfmrnXthfAupyUTzJ/J4Nc1RsHC/mSRU2dll/s=
 github.com/spf13/cobra v1.10.1/go.mod h1:7SmJGaTHFVBY0jW4NXGluQoLvhqFQM+6XSKD+P4XaB0=
 github.com/spf13/pflag v1.0.9 h1:9exaQaMOCwffKiiiYk6/BndUBv+iRViNW+4lEMi0PvY=

internal/api/handlers.go

@@ -30,18 +30,33 @@ type Server struct {
 }
 
 type SearchInput struct {
-	Query         string   `query:"q" minLength:"1" doc:"Search query" example:"mountain"`
-	Limit         int      `query:"limit" default:"10" minimum:"1" maximum:"500" doc:"Maximum results"`
-	Field         string   `query:"field" enum:"filename,body" doc:"Search specific field (empty for all)"`
-	ContentType   string   `query:"content_type" doc:"Filter by MIME type" example:"image/jpeg"`
-	Extension     string   `query:"ext" doc:"Filter by file extension" example:".jpg"`
-	Fuzzy         bool     `query:"fuzzy" doc:"Enable fuzzy matching for typos"`
-	SortBy        string   `query:"sort" enum:"score,mtime,size,filename," default:"score" doc:"Sort results by field"`
-	SortDesc      bool     `query:"desc" default:"true" doc:"Sort descending"`
-	MinSize       int64    `query:"min_size" doc:"Minimum file size in bytes"`
-	MaxSize       int64    `query:"max_size" doc:"Maximum file size in bytes"`
-	ModifiedAfter string   `query:"modified_after" doc:"Filter by modification date (RFC3339)" example:"2024-01-01T00:00:00Z"`
-	Facets        []string `query:"facets" doc:"Enable facets for fields" example:"content_type"`
+	Query           string   `query:"q" minLength:"1" doc:"Search query" example:"mountain"`
+	Limit           int      `query:"limit" default:"10" minimum:"1" maximum:"500" doc:"Maximum results"`
+	Field           string   `query:"field" enum:"filename,body" doc:"Search specific field (empty for all)"`
+	ContentType     string   `query:"content_type" doc:"Filter by MIME type" example:"image/jpeg"`
+	Extension       string   `query:"ext" doc:"Filter by file extension" example:".jpg"`
+	Fuzzy           bool     `query:"fuzzy" doc:"Enable fuzzy matching for typos"`
+	SortBy          string   `query:"sort" enum:"score,mtime,size,filename,exif_date,iso,focal_length,aperture," default:"score" doc:"Sort results by field"`
+	SortDesc        bool     `query:"desc" default:"true" doc:"Sort descending"`
+	MinSize         int64    `query:"min_size" doc:"Minimum file size in bytes"`
+	MaxSize         int64    `query:"max_size" doc:"Maximum file size in bytes"`
+	ModifiedAfter   string   `query:"modified_after" doc:"Filter by modification date (RFC3339)" example:"2024-01-01T00:00:00Z"`
+	Facets          []string `query:"facets" doc:"Enable facets for fields" example:"content_type"`
+	Folder          string   `query:"folder" doc:"Filter by folder path" example:"/home/user/Pictures"`
+	ExifMake        string   `query:"exif_make" doc:"Filter by camera make" example:"Canon"`
+	ExifModel       string   `query:"exif_model" doc:"Filter by camera model" example:"Canon EOS 5D"`
+	ExifDateAfter   string   `query:"exif_date_after" doc:"Photos taken after date" example:"2024-01-01T00:00:00Z"`
+	ExifDateBefore  string   `query:"exif_date_before" doc:"Photos taken before date" example:"2024-12-31T23:59:59Z"`
+	ExifMinISO      int      `query:"exif_min_iso" doc:"Minimum ISO value" example:"100"`
+	ExifMaxISO      int      `query:"exif_max_iso" doc:"Maximum ISO value" example:"3200"`
+	ExifMinAperture float64  `query:"exif_min_aperture" doc:"Minimum aperture (f-number)" example:"1.8"`
+	ExifMaxAperture float64  `query:"exif_max_aperture" doc:"Maximum aperture (f-number)" example:"16"`
+	ExifMinFocalLen float64  `query:"exif_min_focal_len" doc:"Minimum focal length in mm" example:"24"`
+	ExifMaxFocalLen float64  `query:"exif_max_focal_len" doc:"Maximum focal length in mm" example:"200"`
+	ExifLatMin      float64  `query:"exif_lat_min" doc:"Minimum GPS latitude" example:"40.0"`
+	ExifLatMax      float64  `query:"exif_lat_max" doc:"Maximum GPS latitude" example:"41.0"`
+	ExifLonMin      float64  `query:"exif_lon_min" doc:"Minimum GPS longitude" example:"-74.0"`
+	ExifLonMax      float64  `query:"exif_lon_max" doc:"Maximum GPS longitude" example:"-73.0"`
 }
 
 type SearchOutput struct {
@@ -80,18 +95,33 @@ func RegisterHandlers(srv *Server, api huma.API) {
 		Tags:        []string{"Search"},
 	}, func(ctx context.Context, input *SearchInput) (*SearchOutput, error) {
 		opts := &indexer.SearchOptions{
-			Query:         input.Query,
-			Limit:         input.Limit,
-			Field:         input.Field,
-			ContentType:   input.ContentType,
-			Extension:     input.Extension,
-			Fuzzy:         input.Fuzzy,
-			SortBy:        input.SortBy,
-			SortDesc:      input.SortDesc,
-			MinSize:       input.MinSize,
-			MaxSize:       input.MaxSize,
-			ModifiedAfter: input.ModifiedAfter,
-			Facets:        input.Facets,
+			Query:           input.Query,
+			Limit:           input.Limit,
+			Field:           input.Field,
+			ContentType:     input.ContentType,
+			Extension:       input.Extension,
+			Fuzzy:           input.Fuzzy,
+			SortBy:          input.SortBy,
+			SortDesc:        input.SortDesc,
+			MinSize:         input.MinSize,
+			MaxSize:         input.MaxSize,
+			ModifiedAfter:   input.ModifiedAfter,
+			Facets:          input.Facets,
+			Folder:          input.Folder,
+			ExifMake:        input.ExifMake,
+			ExifModel:       input.ExifModel,
+			ExifDateAfter:   input.ExifDateAfter,
+			ExifDateBefore:  input.ExifDateBefore,
+			ExifMinISO:      input.ExifMinISO,
+			ExifMaxISO:      input.ExifMaxISO,
+			ExifMinAperture: input.ExifMinAperture,
+			ExifMaxAperture: input.ExifMaxAperture,
+			ExifMinFocalLen: input.ExifMinFocalLen,
+			ExifMaxFocalLen: input.ExifMaxFocalLen,
+			ExifLatMin:      input.ExifLatMin,
+			ExifLatMax:      input.ExifLatMax,
+			ExifLonMin:      input.ExifLonMin,
+			ExifLonMax:      input.ExifLonMax,
 		}
 
 		result, err := srv.Indexer.SearchWithOptions(opts)