create normalized DwCA (close #11)

Normalized data also closes disambituation of scientific
names, hiearchies and synonyms (close #5, close #6, close #7)

README.md

@@ -1,3 +1,11 @@
 # DwCA is a Go library to deal with Darwin Core Archive files.
 
 
+## Testing
+
+To avoid conflicts in filesystem run tests in sequential order.
+
+```bash
+go test -p 1 -count=1 ./...
+```
+

config/config.go

@@ -5,39 +5,58 @@ import (
 	"path/filepath"
 )
 
+// Config is a configuration object for the Darwin Core Archive (DwCA)
+// data processing.
 type Config struct {
-	Path         string
+	// RootPath is the root path for all temporary files.
+	RootPath string
+
+	// DownloadPath is used to store downloaded files.
 	DownloadPath string
-	ExtractPath  string
-	WithCleanup  bool
+
+	// ExtractPath is used to store extracted files of DwCA archive.
+	ExtractPath string
+
+	// OutputPath is used to store uncompressed files of a normalized
+	// DwCA archive. This files are created from the original DwCA archive
+	// data.
+	OutputPath string
+
+	// JobsNum is the number of concurrent jobs to run.
+	JobsNum int
 }
 
+// Option is a function type that allows to standardize how options to
+// the configuration are organized.
 type Option func(*Config)
 
+// OptPath sets the root path for all temporary files.
 func OptPath(s string) Option {
 	return func(c *Config) {
-		c.Path = s
-	}
-}
-
-func OptWithCleanup(b bool) Option {
-	return func(c *Config) {
-		c.WithCleanup = b
+		c.RootPath = s
 	}
 }
 
+// New creates a new Config object with default values, and allows to
+// override them with options.
 func New(opts ...Option) Config {
 	path, err := os.UserCacheDir()
 	if err != nil {
 		path = os.TempDir()
 	}
 
 	path = filepath.Join(path, "dwca_go")
-	c := Config{Path: path}
+	c := Config{
+		RootPath: path,
+		JobsNum:  5,
+	}
+
 	for _, opt := range opts {
 		opt(&c)
 	}
-	c.DownloadPath = filepath.Join(c.Path, "download")
-	c.ExtractPath = filepath.Join(c.Path, "extract")
+
+	c.DownloadPath = filepath.Join(c.RootPath, "download")
+	c.ExtractPath = filepath.Join(c.RootPath, "extract")
+	c.OutputPath = filepath.Join(c.RootPath, "output")
 	return c
 }

config/config_test.go

@@ -10,13 +10,11 @@ import (
 func TestConfigDefault(t *testing.T) {
 	assert := assert.New(t)
 	conf := config.New()
-	assert.Contains(conf.Path, "dwca_go")
+	assert.Contains(conf.RootPath, "dwca_go")
 
 	opts := []config.Option{
 		config.OptPath("test"),
-		config.OptWithCleanup(true),
 	}
 	conf = config.New(opts...)
-	assert.Equal("test", conf.Path)
-	assert.True(conf.WithCleanup)
+	assert.Equal("test", conf.RootPath)
 }