First version

Author: grongor

.gitignore

@@ -0,0 +1,3 @@
+/bin
+/url-parser
+/url-parser.exe

.travis.yml

@@ -0,0 +1,16 @@
+dist: xenial
+language: go
+
+go:
+    - "1.13"
+    - master
+
+env: GO111MODULE=on
+
+jobs:
+    allow_failures:
+        -   go: master
+
+script:
+    - make
+    - make check

Dockerfile

@@ -0,0 +1,9 @@
+FROM golang AS build
+
+COPY . /app
+RUN cd /app && make
+
+FROM scratch
+
+COPY --from=build /app/url-parser /url-parser
+ENTRYPOINT ["/url-parser"]

Makefile

@@ -0,0 +1,44 @@
+BIN = ${PWD}/bin
+
+.PHONY: build
+build:
+	CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build ./cmd/url-parser
+
+.PHONY: check
+check: cs vet staticcheck test
+
+.PHONY: cs
+cs: tools
+	diff=$$($(BIN)/goimports -d . ); test -z "$$diff" || (echo "$$diff" && exit 1)
+
+.PHONY: cs-fix
+cs-fix: format
+
+.PHONY: format
+format: tools
+	$(BIN)/goimports -w .
+
+.PHONY: vet
+vet:
+	go vet ./...
+
+.PHONY: test
+test:
+	timeout 10 go test
+	timeout 60 go test --race
+	timeout 120 go test --count 1000
+	timeout 10 cmd/url-parser/main_test.sh
+
+.PHONY: staticcheck
+staticcheck: tools
+	$(BIN)/staticcheck ./...
+
+.PHONY: tools
+tools: bin
+
+bin: export GOBIN = $(BIN)
+bin:
+	go install github.com/golang/mock/mockgen
+	go install golang.org/x/lint/golint
+	go install golang.org/x/tools/cmd/goimports
+	go install honnef.co/go/tools/cmd/staticcheck

README.md

@@ -0,0 +1,49 @@
+url-parser
+==========
+
+```
+url-parser
+    Parses given URLs and prints the desired parts of them.
+
+Usage:
+    url-parser <option> [url]...
+
+Options:
+    -c, --component=COMPONENT
+
+        Prints single URL component from each. URL.
+
+        Valid values: scheme, authority, auth, user, password,
+                      hostport, host, tld, port, path, query,
+                      fragment, basePath, file, ext, relativeUrl
+
+        Additionally, some components may be further formatted:
+            host:x, host:x:y            print only desired (sub)domains
+            hostport:x, hostport:x:y    same as host:*, but also includes port
+            path:x, path:x:y            print only desired parts of the path
+            query:NAME                  print only query parameter named NAME
+            fragment:NAME               print only fragment part named NAME
+
+                x    starting position; use -x to start from end
+                y    count; how many parts of the component you want to print
+
+    -f, --format=FORMAT
+
+        Prints URLs formatted according to FORMAT.
+
+        FORMAT is an arbitrary string containing component placeholders
+        enclosed in curly brackets. Each {COMPONENT} will be replaced
+        as if url-parser was called with option -c COMPONENT
+
+Examples:
+
+reference URL: https://www.example.com/lorem/ipsum/dolor/sit.html?metus=lectus#at=nostra&unde=omnis
+
+url-parser -c host:1 <url>               example.com
+url-parser -c path:-0:2 <url>            /dolor/sit.html
+url-parser -c path:-1 <url>              /lorem/ipsum/dolor
+url-parser -c path:0:2 <url>             /lorem/ipsum
+url-parser -c fragment:unde <url>        unde=omnis
+url-parser -c relativeUrl <url>          /lorem/ipsum/dolor/sit.html?metus=lectus#at=nostra&unde=omnis
+url-parser -f {scheme}://{host} <url>    https://www.example.com
+```

cmd/url-parser/main.go

@@ -0,0 +1,96 @@
+package main
+
+import (
+	"bufio"
+	"flag"
+	"fmt"
+	"os"
+
+	urlparser "github.com/grongor/go-url-parser/url-parser"
+)
+
+func usage() {
+	app := "url-parser"
+	fmt.Printf("%s\n    Parses given URLs and prints the desired parts of them.\n\n", app)
+	fmt.Println("Usage:")
+	fmt.Printf("    %s <option> [url]...\n\n", app)
+	fmt.Println("Options:")
+	fmt.Printf("    -c, --component=COMPONENT\n\n")
+	fmt.Printf("        Prints single URL component from each. URL.\n\n")
+	fmt.Println("        Valid values: scheme, authority, auth, user, password,")
+	fmt.Println("                      hostport, host, tld, port, path, query,")
+	fmt.Printf("                      fragment, basePath, file, ext, relativeUrl\n\n")
+	fmt.Printf("        Additionally, some components may be further formatted:\n")
+	fmt.Println("            host:x, host:x:y            print only desired (sub)domains")
+	fmt.Println("            hostport:x, hostport:x:y    same as host:*, but also includes port")
+	fmt.Println("            path:x, path:x:y            print only desired parts of the path")
+	fmt.Println("            query:NAME                  print only query parameter named NAME")
+	fmt.Println("            fragment:NAME               print only fragment part named NAME")
+	fmt.Println("")
+	fmt.Println("                x    starting position; use -x to start from end")
+	fmt.Println("                y    count; how many parts of the component you want to print")
+	fmt.Println("")
+	fmt.Printf("    -f, --format=FORMAT\n\n")
+	fmt.Printf("        Prints URLs formatted according to FORMAT.\n\n")
+	fmt.Println("        FORMAT is an arbitrary string containing component placeholders")
+	fmt.Println("        enclosed in curly brackets. Each {COMPONENT} will be replaced")
+	fmt.Println("        as if url-parser was called with option -c COMPONENT")
+	fmt.Println("")
+	fmt.Printf("Examples:\n\n")
+	fmt.Printf("reference URL: https://www.example.com/lorem/ipsum/dolor/sit.html?metus=lectus#at=nostra&unde=omnis\n\n")
+	fmt.Println("url-parser -c host:1 <url>               example.com")
+	fmt.Println("url-parser -c path:-0:2 <url>            /dolor/sit.html")
+	fmt.Println("url-parser -c path:-1 <url>              /lorem/ipsum/dolor")
+	fmt.Println("url-parser -c path:0:2 <url>             /lorem/ipsum")
+	fmt.Println("url-parser -c fragment:unde <url>        unde=omnis")
+	fmt.Println("url-parser -c relativeUrl <url>          /lorem/ipsum/dolor/sit.html?metus=lectus#at=nostra&unde=omnis")
+	fmt.Println("url-parser -f {scheme}://{host} <url>    https://www.example.com")
+}
+
+var (
+	component string
+	format    string
+)
+
+func main() {
+	flag.StringVar(&component, "component", "", "")
+	flag.StringVar(&component, "c", "", "")
+
+	flag.StringVar(&format, "format", "", "")
+	flag.StringVar(&format, "f", "", "")
+
+	flag.Usage = usage
+	flag.Parse()
+
+	if component == "" && format == "" || component != "" && format != "" {
+		fmt.Fprintln(os.Stderr, "You must specify either --component or --format option.")
+		os.Exit(1)
+	}
+
+	if len(flag.Args()) == 0 {
+		scanner := bufio.NewScanner(os.Stdin)
+		for scanner.Scan() {
+			process(scanner.Text())
+		}
+	} else {
+		for _, rawUrl := range flag.Args() {
+			process(rawUrl)
+		}
+	}
+}
+
+func process(rawUrl string) {
+	var result string
+	var err error
+	if component == "" {
+		result, err = urlparser.Format(rawUrl, format)
+	} else {
+		result, err = urlparser.Component(rawUrl, component)
+	}
+
+	if err != nil {
+		fmt.Fprintln(os.Stderr, err.Error())
+	}
+
+	fmt.Println(result)
+}

cmd/url-parser/main_test.sh

@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+
+set -o errexit
+set -o nounset
+
+cd "$(dirname "$(realpath "$0")")"/../..
+go build ./cmd/url-parser
+
+function clean() {
+    rm -rf ".test-out"
+    rm -rf ".test-err"
+}
+
+trap "clean" EXIT
+
+urls=(
+    "http://www.example.com"
+    "postgres://user:abc{[email protected]"
+    "https://sub.domain.co.uk/path/file.html"
+    "https://"
+)
+
+# component
+
+./url-parser -c "host" > .test-out 2> .test-err <<< IFS="\n" "${urls[@]}"
+
+expected=$'www.example.com\n\nsub.domain.co.uk'
+result="$(cat .test-out)"
+test "$expected" = "$result" || {
+    printf >&2 $"Unexpected parser output:\n\nExpected:\n%s\n\nResult:\n%s\n" "$expected" "$result"
+}
+
+expectedErr=$'parse postgres://user:abc{[email protected]: net/url: invalid userinfo'
+resultErr="$(cat .test-err)"
+test "$expectedErr" = "$resultErr" || {
+    printf >&2 $"Unexpected parser output:\n\nExpected:\n%s\n\nResult:\n%s\n" "$expectedErr" "$resultErr"
+}
+
+# format
+
+./url-parser -f "{scheme} - {tld} - {file}" > .test-out 2> .test-err <<< IFS="\n" "${urls[@]}"
+
+expected=$'http - com - \n\nhttps - co.uk - file.html\nhttps -  - '
+result="$(cat .test-out)"
+test "$expected" = "$result" || {
+    printf >&2 $"Unexpected parser output:\n\nExpected:\n%s\n\nResult:\n%s\n" "$expected" "$result"
+}
+
+expectedErr=$'parse postgres://user:abc{[email protected]: net/url: invalid userinfo'
+resultErr="$(cat .test-err)"
+test "$expectedErr" = "$resultErr" || {
+    printf >&2 $"Unexpected parser output:\n\nExpected:\n%s\n\nResult:\n%s\n" "$expectedErr" "$resultErr"
+}