fix cmd descriptions

Author: sholokhov

checks.yaml

@@ -1,21 +1,22 @@
-version: 0.1
+version: "1"
 validations:
-  - dataset: clickhouse-prod-euw:ads.my_table_1
+  - dataset: clickhouse-prod-euw@[ads.my_table_1]
+    where: "timestamp > '2025-01-01'"
     checks:
-      - id: row number between 0 and 100
-        severity: warn
+      - id: row count between 0 and 100
+        severity: error
         type: row_count
         params:
-            filter: "timestamp > '2023-01-01'"
+            # filter: "timestamp > '2023-01-01'"
             min: 0
             max: 100
 
       - id: "no null values"
-        description: "Check if table_1 has the correct number of columns"
+        description: "Check if table_1 has the correct number of columns" # optional
         severity: error
         type: custom
         params:
-          query: SELECT COUNT(*) FROM table_1 WHERE column_name IS NULL
+          query: SELECT COUNT(*) FROM ${table} WHERE column_name IS NULL
           expected: 0
 
       - id: "no duplicates"
@@ -24,7 +25,7 @@ validations:
         type: no_duplicates
         params:
           columns: ["column_1", "column_2"]
-          filter: "timestamp > '2023-01-01'"
+          # filter: "timestamp > '2023-01-01'"
 
   - dataset: pgsql-staging@[public.table_1, public.table_2]
     checks:

cmd/check.go

@@ -13,13 +13,12 @@ func NewCheckCommand(app internal.DbqApp) *cobra.Command {
 
 	cmd := &cobra.Command{
 		Use:   "check",
-		Short: "A brief description of your command",
-		Long: `A longer description that spans multiple lines and likely contains examples
-and usage of using your command. For example:
+		Short: "Runs data quality checks defined in a configuration file against a datasource",
+		Long: `The 'check' command executes a series of data quality tests or checks as defined in a specified configuration file against a target dataset. This command reads the configuration file, 
+which outlines the rules and constraints that the data within the dataset should adhere to. For each defined check, the command analyzes the dataset and reports any violations or inconsistencies found.
 
-Cobra is a CLI library for Go that empowers applications.
-This application is a tool to generate the needed files
-to quickly create a Cobra application.`,
+By automating these checks, you can proactively identify and address data quality issues, ensuring that your datasets meet the required standards for analysis and decision-making.
+`,
 		RunE: func(cmd *cobra.Command, args []string) error {
 			fmt.Println("Reading checks from " + checksFile)
 			if dataSource != "" {

cmd/import.go

@@ -14,13 +14,11 @@ func NewImportCommand(app internal.DbqApp) *cobra.Command {
 
 	cmd := &cobra.Command{
 		Use:   "import",
-		Short: "A brief description of your command",
-		Long: `A longer description that spans multiple lines and likely contains examples
-and usage of using your command. For example:
+		Short: "Connects to a data source and imports all available tables as datasets",
+		Long: `The 'import' command establishes a connection to the specified data source using the provided connection parameters. It retrieves a list of all available tables within the data source and transforms them into datasets within dbq.
 
-Cobra is a CLI library for Go that empowers applications.
-This application is a tool to generate the needed files
-to quickly create a Cobra application.`,
+This command is useful for quickly onboarding data from external systems, allowing you to easily access and work with already existing data.
+`,
 		RunE: func(cmd *cobra.Command, args []string) error {
 			datasets, err := app.ImportDatasets(dataSource, filter)
 			if err != nil {

cmd/ping.go

@@ -2,28 +2,36 @@ package cmd
 
 import (
 	"dbq/internal"
-	"fmt"
 	"github.com/spf13/cobra"
+	"log"
 )
 
 func NewPingCommand(app internal.DbqApp) *cobra.Command {
 	var dataSource string
 
 	cmd := &cobra.Command{
 		Use:   "ping",
-		Short: "A brief description of your command",
-		Long: `A longer description that spans multiple lines and likely contains examples
-and usage of using your command. For example:
-
-Cobra is a CLI library for Go that empowers applications.
-This application is a tool to generate the needed files
-to quickly create a Cobra application.`,
+		Short: "Checks if the data source is reachable",
+		Long: `The 'ping' command sends a network request to the configured data source to verify its reachability. 
+This is useful for quickly determining if the data source is online and responding. It provides a simple status indication of the connection`,
 		Run: func(cmd *cobra.Command, args []string) {
-			err := app.PingDataSource(dataSource)
-			if err != nil {
-				fmt.Printf("Connection failed: %s\n", err.Error())
+			var sourcesToPing []string
+			if dataSource != "" {
+				sourcesToPing = append(sourcesToPing, dataSource)
 			} else {
-				fmt.Println("Connection works")
+				for _, ds := range app.GetDbqConfig().DataSources {
+					sourcesToPing = append(sourcesToPing, ds.ID)
+				}
+			}
+
+			for _, curDataSource := range sourcesToPing {
+				log.Printf("Pinging data source: %s...\n", curDataSource)
+				info, err := app.PingDataSource(curDataSource)
+				if err != nil {
+					log.Printf("Connection failed: %s\n", err.Error())
+				} else {
+					log.Printf("Connected: %s\n", info)
+				}
 			}
 		},
 	}

cmd/profile.go

@@ -13,13 +13,14 @@ func NewProfileCommand(app internal.DbqApp) *cobra.Command {
 
 	cmd := &cobra.Command{
 		Use:   "profile",
-		Short: "A brief description of your command",
-		Long: `A longer description that spans multiple lines and likely contains examples
-and usage of using your command. For example:
+		Short: "Collects dataset's information and generates column statistics",
+		Long: `The 'profile' command connects to the specified data source and analyzes a given dataset. It gathers essential information about the table, such as the total number of rows. 
+Additionally, for each column within the table, it calculates and reports various statistical metrics. These metrics may include the minimum value, maximum value, the count of null or missing values, the data type, 
+and other relevant statistics depending on the data type and the capabilities of the underlying data source.
 
-Cobra is a CLI library for Go that empowers applications.
-This application is a tool to generate the needed files
-to quickly create a Cobra application.`,
+This command is useful for understanding the characteristics and quality of your data. It provides a quick overview of the data distribution, identifies potential data quality issues like missing values, 
+and helps in making better decisions about data processing and analysis.
+`,
 		RunE: func(cmd *cobra.Command, args []string) error {
 			var dataSetsToProfile []string
 			if dataSet != "" {

cmd/root.go

@@ -9,13 +9,7 @@ import (
 
 var rootCmd = &cobra.Command{
 	Use:   "dbq",
-	Short: "A brief description of your application",
-	Long: `A longer description that spans multiple lines and likely contains
-examples and usage of using your application. For example:
-
-Cobra is a CLI library for Go that empowers applications.
-This application is a tool to generate the needed files
-to quickly create a Cobra application.`,
+	Short: "dbq is a CLI tool for profiling data and running quality checks across various data sources",
 }
 
 func Execute() {

cmd/version.go

@@ -8,13 +8,7 @@ import (
 func NewVersionCommand() *cobra.Command {
 	cmd := &cobra.Command{
 		Use:   "version",
-		Short: "A brief description of your command",
-		Long: `A longer description that spans multiple lines and likely contains examples
-and usage of using your command. For example:
-
-Cobra is a CLI library for Go that empowers applications.
-This application is a tool to generate the needed files
-to quickly create a Cobra application.`,
+		Short: "Prints dbq version",
 		Run: func(cmd *cobra.Command, args []string) {
 			fmt.Println("DataBridge Quality Core: 0.0.1")
 		},

dbq.yaml

@@ -11,6 +11,7 @@ datasources:
       datasets:
         - default.my_first_table
         - default.trips_small
+        - uk.uk_price_paid
     - id: pgsql
       type: postgres
       configuration:

internal/app.go

@@ -6,13 +6,12 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/spf13/viper"
 	"gopkg.in/yaml.v3"
-	"log"
 	"os"
 	"strings"
 )
 
 type DbqApp interface {
-	PingDataSource(srcId string) error
+	PingDataSource(srcId string) (string, error)
 	ImportDatasets(srcId string, filter string) ([]string, error)
 	ProfileDataSourceById(srcId string, dataset string) (*TableMetrics, error)
 	GetDbqConfig() *DbqConfig
@@ -33,21 +32,20 @@ func NewDbqApp(dbqConfigPath string) DbqApp {
 	}
 }
 
-func (app *DbqAppImpl) PingDataSource(srcId string) error {
+func (app *DbqAppImpl) PingDataSource(srcId string) (string, error) {
 	var dataSource = app.FindDataSourceById(srcId)
 
 	cnn, err := getDbqConnector(*dataSource)
 	if err != nil {
-		return err
+		return "", err
 	}
 
-	log.Println("Pinging datasource: " + dataSource.ID)
-	err = cnn.Ping()
+	info, err := cnn.Ping()
 	if err != nil {
-		return err
+		return "", err
 	}
 
-	return nil
+	return info, nil
 }
 
 func (app *DbqAppImpl) ImportDatasets(srcId string, filter string) ([]string, error) {

internal/clickhouse.go

@@ -33,8 +33,18 @@ func NewClickhouseDbqConnector(dataSource DataSource) (DbqConnector, error) {
 	}, err
 }
 
-func (c *ClickhouseDbqConnector) Ping() error {
-	return c.cnn.Ping(context.Background())
+func (c *ClickhouseDbqConnector) Ping() (string, error) {
+	err := c.cnn.Ping(context.Background())
+	if err != nil {
+		return "", err
+	}
+
+	info, err := c.cnn.ServerVersion()
+	if err != nil {
+		return "", err
+	}
+
+	return info.String(), nil
 }
 
 func (c *ClickhouseDbqConnector) ImportDataSets(filter string) ([]string, error) {