Compare commits
17 Commits
9b08b40b5e
...
0.1.1
Author | SHA1 | Date | |
---|---|---|---|
64efaf5514 | |||
8d320f96cd | |||
75c5e7ea4c | |||
e6e668451a | |||
9528fca452 | |||
cf95ee2acb | |||
4a673d1894 | |||
0d22da3643 | |||
0107f77570 | |||
d5f658244b | |||
72128f97a3 | |||
78e2568e2b | |||
75ba450d9b | |||
dd7f0c0a28 | |||
3f072184e0 | |||
9d932ec70e | |||
4094141c0b |
38
.gitea/workflows/release.yml
Normal file
38
.gitea/workflows/release.yml
Normal file
@@ -0,0 +1,38 @@
|
|||||||
|
name: Release
|
||||||
|
|
||||||
|
on:
|
||||||
|
push:
|
||||||
|
tags:
|
||||||
|
- "*"
|
||||||
|
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
changelog:
|
||||||
|
name: Generate changelog
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
permissions:
|
||||||
|
contents: write
|
||||||
|
steps:
|
||||||
|
- name: Checkout
|
||||||
|
uses: actions/checkout@v4
|
||||||
|
with:
|
||||||
|
fetch-depth: 0
|
||||||
|
|
||||||
|
- name: Generate changelog
|
||||||
|
uses: orhun/git-cliff-action@v4
|
||||||
|
with:
|
||||||
|
config: cliff.toml
|
||||||
|
args: --verbose
|
||||||
|
env:
|
||||||
|
OUTPUT: CHANGELOG.md
|
||||||
|
GITHUB_REPO: ${{ github.repository }}
|
||||||
|
|
||||||
|
- name: Commit
|
||||||
|
run: |
|
||||||
|
git checkout <branch>
|
||||||
|
git config user.name 'github-actions[bot]'
|
||||||
|
git config user.email 'github-actions[bot]@users.noreply.github.com'
|
||||||
|
set +e
|
||||||
|
git add CHANGELOG.md
|
||||||
|
git commit -m "Update changelog"
|
||||||
|
git push https://${{ secrets.GITHUB_TOKEN }}@github.com/${GITHUB_REPOSITORY}.git <branch>
|
@@ -10,7 +10,7 @@ on:
|
|||||||
jobs:
|
jobs:
|
||||||
renovate:
|
renovate:
|
||||||
runs-on: ubuntu-latest
|
runs-on: ubuntu-latest
|
||||||
container: ghcr.io/renovatebot/renovate:39.211.0
|
container: ghcr.io/renovatebot/renovate:39.216.1
|
||||||
steps:
|
steps:
|
||||||
- uses: actions/checkout@v4
|
- uses: actions/checkout@v4
|
||||||
- run: renovate
|
- run: renovate
|
||||||
|
25
.gitea/workflows/sonarqube.yaml
Normal file
25
.gitea/workflows/sonarqube.yaml
Normal file
@@ -0,0 +1,25 @@
|
|||||||
|
on:
|
||||||
|
push:
|
||||||
|
branches:
|
||||||
|
- main
|
||||||
|
pull_request:
|
||||||
|
types: [opened, synchronize, reopened]
|
||||||
|
|
||||||
|
name: SonarQube Scan
|
||||||
|
jobs:
|
||||||
|
build:
|
||||||
|
name: Build and analyze
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
|
||||||
|
steps:
|
||||||
|
- uses: actions/checkout@v4
|
||||||
|
with:
|
||||||
|
fetch-depth: 0 # Shallow clones should be disabled for a better relevancy of analysis
|
||||||
|
- uses: SonarSource/sonarqube-scan-action@v4
|
||||||
|
env:
|
||||||
|
SONAR_TOKEN: ${{ secrets.SONARQUBE_TOKEN }}
|
||||||
|
SONAR_HOST_URL: ${{ secrets.SONARQUBE_HOST }}
|
||||||
|
- uses: SonarSource/sonarqube-quality-gate-action@v1
|
||||||
|
timeout-minutes: 5
|
||||||
|
env:
|
||||||
|
SONAR_TOKEN: ${{ secrets.SONARQUBE_TOKEN }}
|
45
CHANGELOG.md
Normal file
45
CHANGELOG.md
Normal file
@@ -0,0 +1,45 @@
|
|||||||
|
# Changelog
|
||||||
|
|
||||||
|
All notable changes to this project will be documented in this file.
|
||||||
|
|
||||||
|
## [unreleased]
|
||||||
|
|
||||||
|
### 🚀 Features
|
||||||
|
|
||||||
|
- *(index)* Add save and load functionality for Index using gob encoding/decoding
|
||||||
|
|
||||||
|
### 📚 Documentation
|
||||||
|
|
||||||
|
- Add first release in Changelog
|
||||||
|
|
||||||
|
## [0.1.0] - 2025-03-25
|
||||||
|
|
||||||
|
### 🚀 Features
|
||||||
|
|
||||||
|
- Added documentation for gosearch system architecture and updated Go module version to 1.23.5
|
||||||
|
- Update internal HTTP server to use Fiber v2 with new routes and middleware configuration
|
||||||
|
- Added new search route and metric endpoint to internal controller
|
||||||
|
- Update fiber version from 2 to 3 and add health checks
|
||||||
|
- Added search functionality with TF-IDF scoring and inverted index data structure for efficient document retrieval.
|
||||||
|
- Update Fiber version to v2 and update internal controller and search logic to use new index module
|
||||||
|
- Update search.go to include debug logging for relevance scores
|
||||||
|
- *(doc)* Update diagram explanation for improved clarity
|
||||||
|
|
||||||
|
### 🚜 Refactor
|
||||||
|
|
||||||
|
- Search controller to convert query to lowercase
|
||||||
|
- Index and removed old functions
|
||||||
|
|
||||||
|
### 📚 Documentation
|
||||||
|
|
||||||
|
- Added high-level architecture diagram for Elasticsearch SearchEngine in Go, including components and interactions
|
||||||
|
|
||||||
|
### ⚙️ Miscellaneous Tasks
|
||||||
|
|
||||||
|
- Update dependencies to latest versions (go.mod, go.sum)
|
||||||
|
- Added golang workflow for building and testing project
|
||||||
|
- Update Go version in build-and-test workflow to 1.23
|
||||||
|
- Added renovate configuration files for Gitea workflow automation
|
||||||
|
- Add release pipeline
|
||||||
|
|
||||||
|
<!-- generated by git-cliff -->
|
@@ -1,5 +1,7 @@
|
|||||||
# gosearch
|
# gosearch
|
||||||
|
|
||||||
|
[](https://sonar.dev-null.rocks/dashboard?id=gosearch)
|
||||||
|
|
||||||
### Diagram of the Architecture
|
### Diagram of the Architecture
|
||||||
|
|
||||||
```mermaid
|
```mermaid
|
||||||
|
84
cliff.toml
Normal file
84
cliff.toml
Normal file
@@ -0,0 +1,84 @@
|
|||||||
|
# git-cliff ~ default configuration file
|
||||||
|
# https://git-cliff.org/docs/configuration
|
||||||
|
#
|
||||||
|
# Lines starting with "#" are comments.
|
||||||
|
# Configuration options are organized into tables and keys.
|
||||||
|
# See documentation for more information on available options.
|
||||||
|
|
||||||
|
[changelog]
|
||||||
|
# template for the changelog header
|
||||||
|
header = """
|
||||||
|
# Changelog\n
|
||||||
|
All notable changes to this project will be documented in this file.\n
|
||||||
|
"""
|
||||||
|
# template for the changelog body
|
||||||
|
# https://keats.github.io/tera/docs/#introduction
|
||||||
|
body = """
|
||||||
|
{% if version %}\
|
||||||
|
## [{{ version | trim_start_matches(pat="v") }}] - {{ timestamp | date(format="%Y-%m-%d") }}
|
||||||
|
{% else %}\
|
||||||
|
## [unreleased]
|
||||||
|
{% endif %}\
|
||||||
|
{% for group, commits in commits | group_by(attribute="group") %}
|
||||||
|
### {{ group | striptags | trim | upper_first }}
|
||||||
|
{% for commit in commits %}
|
||||||
|
- {% if commit.scope %}*({{ commit.scope }})* {% endif %}\
|
||||||
|
{% if commit.breaking %}[**breaking**] {% endif %}\
|
||||||
|
{{ commit.message | upper_first }}\
|
||||||
|
{% endfor %}
|
||||||
|
{% endfor %}\n
|
||||||
|
"""
|
||||||
|
# template for the changelog footer
|
||||||
|
footer = """
|
||||||
|
<!-- generated by git-cliff -->
|
||||||
|
"""
|
||||||
|
# remove the leading and trailing s
|
||||||
|
trim = true
|
||||||
|
# postprocessors
|
||||||
|
postprocessors = [
|
||||||
|
# { pattern = '<REPO>', replace = "https://github.com/orhun/git-cliff" }, # replace repository URL
|
||||||
|
]
|
||||||
|
# render body even when there are no releases to process
|
||||||
|
# render_always = true
|
||||||
|
# output file path
|
||||||
|
# output = "test.md"
|
||||||
|
|
||||||
|
[git]
|
||||||
|
# parse the commits based on https://www.conventionalcommits.org
|
||||||
|
conventional_commits = true
|
||||||
|
# filter out the commits that are not conventional
|
||||||
|
filter_unconventional = true
|
||||||
|
# process each line of a commit as an individual commit
|
||||||
|
split_commits = false
|
||||||
|
# regex for preprocessing the commit messages
|
||||||
|
commit_preprocessors = [
|
||||||
|
# Replace issue numbers
|
||||||
|
#{ pattern = '\((\w+\s)?#([0-9]+)\)', replace = "([#${2}](<REPO>/issues/${2}))"},
|
||||||
|
# Check spelling of the commit with https://github.com/crate-ci/typos
|
||||||
|
# If the spelling is incorrect, it will be automatically fixed.
|
||||||
|
#{ pattern = '.*', replace_command = 'typos --write-changes -' },
|
||||||
|
]
|
||||||
|
# regex for parsing and grouping commits
|
||||||
|
commit_parsers = [
|
||||||
|
{ message = "^feat", group = "<!-- 0 -->🚀 Features" },
|
||||||
|
{ message = "^fix", group = "<!-- 1 -->🐛 Bug Fixes" },
|
||||||
|
{ message = "^doc", group = "<!-- 3 -->📚 Documentation" },
|
||||||
|
{ message = "^perf", group = "<!-- 4 -->⚡ Performance" },
|
||||||
|
{ message = "^refactor", group = "<!-- 2 -->🚜 Refactor" },
|
||||||
|
{ message = "^style", group = "<!-- 5 -->🎨 Styling" },
|
||||||
|
{ message = "^test", group = "<!-- 6 -->🧪 Testing" },
|
||||||
|
{ message = "^chore\\(release\\): prepare for", skip = true },
|
||||||
|
{ message = "^chore\\(deps.*\\)", skip = true },
|
||||||
|
{ message = "^chore\\(pr\\)", skip = true },
|
||||||
|
{ message = "^chore\\(pull\\)", skip = true },
|
||||||
|
{ message = "^chore|^ci", group = "<!-- 7 -->⚙️ Miscellaneous Tasks" },
|
||||||
|
{ body = ".*security", group = "<!-- 8 -->🛡️ Security" },
|
||||||
|
{ message = "^revert", group = "<!-- 9 -->◀️ Revert" },
|
||||||
|
{ message = ".*", group = "<!-- 10 -->💼 Other" },
|
||||||
|
]
|
||||||
|
# filter out the commits that are not matched by commit parsers
|
||||||
|
filter_commits = false
|
||||||
|
# sort the tags topologically
|
||||||
|
topo_order = false
|
||||||
|
# sort the commits inside sections by oldest/newest order
|
||||||
|
sort_commits = "oldest"
|
@@ -12,7 +12,7 @@ import (
|
|||||||
|
|
||||||
func SearchQuery(c *fiber.Ctx) error {
|
func SearchQuery(c *fiber.Ctx) error {
|
||||||
query := c.Params("query")
|
query := c.Params("query")
|
||||||
query = strings.TrimSpace(strings.ToLower(query))
|
query = strings.TrimSpace(query)
|
||||||
|
|
||||||
terms, queryType := parseQuery(query)
|
terms, queryType := parseQuery(query)
|
||||||
results := search.Search(terms, queryType, index.Index, index.DocFreq, len(index.Documents))
|
results := search.Search(terms, queryType, index.Index, index.DocFreq, len(index.Documents))
|
||||||
@@ -29,12 +29,12 @@ func SearchQuery(c *fiber.Ctx) error {
|
|||||||
|
|
||||||
// parseQuery parses the query to determine query type and terms
|
// parseQuery parses the query to determine query type and terms
|
||||||
func parseQuery(query string) ([]string, string) {
|
func parseQuery(query string) ([]string, string) {
|
||||||
if strings.Contains(query, "AND") {
|
if strings.Contains(strings.ToLower(query), "AND") {
|
||||||
return strings.Split(query, " AND "), "AND"
|
return strings.Split(strings.ToLower(query), " AND "), "AND"
|
||||||
} else if strings.Contains(query, "OR") {
|
} else if strings.Contains(strings.ToLower(query), "OR") {
|
||||||
return strings.Split(query, " OR "), "OR"
|
return strings.Split(strings.ToLower(query), " OR "), "OR"
|
||||||
}
|
}
|
||||||
return strings.Fields(query), "SIMPLE"
|
return strings.Fields(strings.ToLower(query)), "SIMPLE"
|
||||||
}
|
}
|
||||||
|
|
||||||
// phraseMatch checks if all terms appear in the given document in sequence
|
// phraseMatch checks if all terms appear in the given document in sequence
|
||||||
|
@@ -2,6 +2,7 @@ package http
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"github.com/gofiber/fiber/v2"
|
"github.com/gofiber/fiber/v2"
|
||||||
|
"github.com/gofiber/fiber/v2/log"
|
||||||
"github.com/gofiber/fiber/v2/middleware/logger"
|
"github.com/gofiber/fiber/v2/middleware/logger"
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -12,6 +13,7 @@ func StartService() {
|
|||||||
app.Use(logger.New(logger.Config{
|
app.Use(logger.New(logger.Config{
|
||||||
Format: "[${ip}]:${port} ${status} - ${method} ${path}\n",
|
Format: "[${ip}]:${port} ${status} - ${method} ${path}\n",
|
||||||
}))
|
}))
|
||||||
|
log.SetLevel(log.LevelInfo)
|
||||||
|
|
||||||
// Configure Routes
|
// Configure Routes
|
||||||
app = configureRoutes(app)
|
app = configureRoutes(app)
|
||||||
|
2
main.go
2
main.go
@@ -7,7 +7,7 @@ import (
|
|||||||
|
|
||||||
func main() {
|
func main() {
|
||||||
// Initialize Index
|
// Initialize Index
|
||||||
index.CreateIndex()
|
index.InitIndex("default")
|
||||||
|
|
||||||
// Start HTTP Server
|
// Start HTTP Server
|
||||||
http.StartService()
|
http.StartService()
|
||||||
|
@@ -2,6 +2,12 @@ package index
|
|||||||
|
|
||||||
import (
|
import (
|
||||||
"bufio"
|
"bufio"
|
||||||
|
"bytes"
|
||||||
|
"encoding/gob"
|
||||||
|
"errors"
|
||||||
|
"fmt"
|
||||||
|
"log"
|
||||||
|
"os"
|
||||||
"strings"
|
"strings"
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -13,7 +19,40 @@ var Index InvertedIndex
|
|||||||
var DocFreq DocumentFrequency
|
var DocFreq DocumentFrequency
|
||||||
var Documents []string
|
var Documents []string
|
||||||
|
|
||||||
func CreateIndex() {
|
type SavedIndex struct {
|
||||||
|
Index InvertedIndex
|
||||||
|
DocFreq DocumentFrequency
|
||||||
|
Documents []string
|
||||||
|
}
|
||||||
|
|
||||||
|
func InitIndex(name string) {
|
||||||
|
createIndex()
|
||||||
|
|
||||||
|
// check if index as file exists
|
||||||
|
// if not, create one and save it
|
||||||
|
indexFilePath := "/tmp/" + name + ".db"
|
||||||
|
if _, err := os.Stat(indexFilePath); errors.Is(err, os.ErrNotExist) {
|
||||||
|
f, err := os.Create(indexFilePath)
|
||||||
|
if err != nil {
|
||||||
|
log.Fatal(err)
|
||||||
|
}
|
||||||
|
defer f.Close()
|
||||||
|
} else {
|
||||||
|
var savedIndex SavedIndex
|
||||||
|
|
||||||
|
err = readStructFromFile(indexFilePath, &savedIndex)
|
||||||
|
if err != nil {
|
||||||
|
fmt.Println("Fehler beim Lesen:", err)
|
||||||
|
return
|
||||||
|
}
|
||||||
|
|
||||||
|
Index = savedIndex.Index
|
||||||
|
DocFreq = savedIndex.DocFreq
|
||||||
|
Documents = savedIndex.Documents
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func createIndex() {
|
||||||
index := make(InvertedIndex)
|
index := make(InvertedIndex)
|
||||||
docFreq := make(DocumentFrequency)
|
docFreq := make(DocumentFrequency)
|
||||||
var docs []string
|
var docs []string
|
||||||
@@ -23,6 +62,21 @@ func CreateIndex() {
|
|||||||
DocFreq = docFreq
|
DocFreq = docFreq
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func updateIndex(name string) {
|
||||||
|
savedIndex := SavedIndex{
|
||||||
|
Index: Index,
|
||||||
|
DocFreq: DocFreq,
|
||||||
|
Documents: Documents,
|
||||||
|
}
|
||||||
|
|
||||||
|
indexFilePath := "/tmp/" + name + ".db"
|
||||||
|
err := writeStructToFile(indexFilePath, savedIndex)
|
||||||
|
if err != nil {
|
||||||
|
fmt.Println("Fehler beim Schreiben:", err)
|
||||||
|
return
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
func AddDocToIndex(url string, content string) {
|
func AddDocToIndex(url string, content string) {
|
||||||
Documents = append(Documents, url)
|
Documents = append(Documents, url)
|
||||||
|
|
||||||
@@ -33,7 +87,7 @@ func AddDocToIndex(url string, content string) {
|
|||||||
scanner.Split(bufio.ScanWords)
|
scanner.Split(bufio.ScanWords)
|
||||||
|
|
||||||
for scanner.Scan() {
|
for scanner.Scan() {
|
||||||
word := strings.ToLower(strings.Trim(scanner.Text(), ",.!?"))
|
word := strings.ToLower(strings.Trim(scanner.Text(), ",.!?&<>;:=§$%{}[]()|"))
|
||||||
|
|
||||||
if Index[word] == nil {
|
if Index[word] == nil {
|
||||||
Index[word] = make(map[string]int)
|
Index[word] = make(map[string]int)
|
||||||
@@ -46,4 +100,35 @@ func AddDocToIndex(url string, content string) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
go updateIndex("default")
|
||||||
|
}
|
||||||
|
|
||||||
|
func writeStructToFile(filename string, data interface{}) error {
|
||||||
|
var buf bytes.Buffer
|
||||||
|
enc := gob.NewEncoder(&buf)
|
||||||
|
err := enc.Encode(data)
|
||||||
|
if err != nil {
|
||||||
|
return fmt.Errorf("error when encoding the structs: %w", err)
|
||||||
|
}
|
||||||
|
|
||||||
|
err = os.WriteFile(filename, buf.Bytes(), 0644)
|
||||||
|
if err != nil {
|
||||||
|
return fmt.Errorf("error when writing to the file: %w", err)
|
||||||
|
}
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
|
func readStructFromFile(filename string, data interface{}) error {
|
||||||
|
content, err := os.ReadFile(filename)
|
||||||
|
if err != nil {
|
||||||
|
return fmt.Errorf("error reading the file: %w", err)
|
||||||
|
}
|
||||||
|
|
||||||
|
buf := bytes.NewBuffer(content)
|
||||||
|
dec := gob.NewDecoder(buf)
|
||||||
|
err = dec.Decode(data)
|
||||||
|
if err != nil {
|
||||||
|
return fmt.Errorf("error when decoding the structs: %w", err)
|
||||||
|
}
|
||||||
|
return nil
|
||||||
}
|
}
|
||||||
|
1
sonar-project.properties
Normal file
1
sonar-project.properties
Normal file
@@ -0,0 +1 @@
|
|||||||
|
sonar.projectKey=gosearch
|
Reference in New Issue
Block a user