Maarso 19, 2025
Sida Aan Usoo Bandhignay 50 Luuqadood
Markii aan go’aansanay in aan website-keena GoHugo.io ku dhigno luuqado badan, waxaan dooneynay hab hufan, ballaaran, oo kharash-ku-ool ah si aan u abuurno turjumaado. Halkii aan gacanta ku turjumi lahayn bog kasta, waxaan ka faa’iideysanay API-ga OpenAI si aan hawsha u toosino. Maqaalkaan wuxuu sharxayaa sida aan OpenAI API ugu dhex darney Hugo, anagoo adeegsanayna mawduuca HugoPlate ee Zeon Studio, si aan turjumaadaha si dhaqso leh oo sax ah u soo saarno.
Sababta Aan U Dooranay OpenAI API Turjumida
Adeegyada turjumida dhaqameed badanaa waxay u baahan yihiin dadaal badan oo gacanta ah, qalabka otomaatiga ah sida Google Translate, inkastoo faa’iido leh, mararka qaar ma bixiyaan heerka habeynta aan u baahnayn. API-ga OpenAI wuxuu noo ogolaaday:
- In aan si ballaaran u toosinno turjumaadaha
- In aan habeynno qaabka turjumida
- In aan si fiican u xakameyno tayada
- In si habsami leh loogu dhex daro website-keena ku saleysan Hugo
- In bogag gaar ah loo calaamadiyo in dib loo turjumo
- In luuqado cusub lagu daro dadaal yar
Habka Talaabo-Talaabo
1. Diyaarinta Website-ka Hugo
Website-keenu hore ayaa loo dejiyey iyadoo la adeegsanayo mawduuca HugoPlate, kaas oo taageera hawsha luuqado badan. Talaabada koowaad waxay ahayd in la hawlgaliyo taageerada luuqadaha faylka config/_default/languages.toml ee Hugo:
```toml
################ English language ##################
[en]
languageName = "English"
languageCode = "en-us"
contentDir = "content/english"
weight = 1
################ Arabic language ##################
[ar]
languageName = "العربية"
languageCode = "ar"
contentDir = "content/arabic"
languageDirection = 'rtl'
weight = 2
```
Qaabeyntan waxay xaqiijineysaa in Hugo uu soo saari karo noocyo luuqado kala duwan leh oo ka mid ah nuxurka.
2. Toosinta Turjumaadaha Iyadoo La Adeegsanayo OpenAI API
Waxaan horumarinay script Bash ah oo si otomaatig ah u turjuma faylasha Markdown. Script-kan:
- Wuxuu akhriyaa faylasha
.mdee Ingiriisiga ah ee ku jira galka ilaha. - Wuxuu adeegsanayaa OpenAI API si uu u turjumo qoraalka isagoo ilaalinaya qaabka Markdown.
- Wuxuu qoraalka turjuman ku qoraa galalka luuqadaha ku habboon.
- Wuxuu la socdaa xaaladda turjumida isagoo adeegsanaya fayl JSON ah.
Halkan waa script-keena bash ee otomaatiga turjumaadaha. Si xor ah u isticmaal oo wax ka beddel sidaad u baahan tahay:
```bash
# MIT License
# Copyright (c) 2024 Williston Technical Inc.
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
#!/bin/bash
# ===========================================
# Hugo Content Translation and Update Script (Sequential Processing & New-Language Cleanup)
# ===========================================
# This script translates Hugo Markdown (.md) files from English to all supported target languages
# sequentially (one file at a time). It updates a JSON status file after processing each file.
# At the end of the run, it checks translation_status.json and removes any language from
# translate_new_language.txt only if every file for that language is marked as "success".
# ===========================================
set -euo pipefail
# --- Simple Logging Function (writes to stderr) ---
log_step() {
echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" >&2
}
# --- Environment Setup ---
export PATH="/opt/homebrew/opt/coreutils/libexec/gnubin:$PATH"
# (Removed "Script starting." log)
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
log_step "SCRIPT_DIR set to: $SCRIPT_DIR"
if [ -f "$SCRIPT_DIR/.env" ]; then
log_step "Loading environment variables from .env"
set -o allexport
source "$SCRIPT_DIR/.env"
set +o allexport
fi
# Load new languages from translate_new_language.txt (if available)
declare -a NEW_LANGUAGES=()
if [ -f "$SCRIPT_DIR/translate_new_language.txt" ]; then
while IFS= read -r line || [[ -n "$line" ]]; do
NEW_LANGUAGES+=("$line")
done <"$SCRIPT_DIR/translate_new_language.txt"
else
log_step "No new languages file found; proceeding with empty NEW_LANGUAGES."
fi
API_KEY="${OPENAI_API_KEY:-}"
if [ -z "$API_KEY" ]; then
log_step "❌ Error: OPENAI_API_KEY environment variable is not set."
exit 1
fi
# Supported Languages (full list)
SUPPORTED_LANGUAGES=("ar" "bg" "bn" "cs" "da" "de" "el" "es" "fa" "fi" "fr" "ha" "he" "hi" "hr" "hu" "id" "ig" "it" "ja" "ko" "ml" "mr" "ms" "nl" "no" "pa" "pl" "pt" "ro" "ru" "sk" "sn" "so" "sr" "sv" "sw" "ta" "te" "th" "tl" "tr" "uk" "vi" "xh" "yo" "zh" "zu")
STATUS_FILE="$SCRIPT_DIR/translation_status.json"
SRC_DIR="$SCRIPT_DIR/Content/english"
log_step "Source directory: $SRC_DIR"
# Check dependencies
for cmd in jq curl; do
if ! command -v "$cmd" >/dev/null 2>&1; then
log_step "❌ Error: '$cmd' is required. Please install it."
exit 1
fi
done
MAX_RETRIES=5
WAIT_TIME=2 # seconds
# Create/initialize status file if missing
if [ ! -f "$STATUS_FILE" ]; then
echo "{}" >"$STATUS_FILE"
log_step "Initialized status file at: $STATUS_FILE"
fi
# --- Locking for Status Updates ---
lock_status() {
local max_wait=10
local start_time
start_time=$(date +%s)
while ! mkdir "$STATUS_FILE.lockdir" 2>/dev/null; do
sleep 0.01
local now
now=$(date +%s)
if ((now - start_time >= max_wait)); then
log_step "WARNING: Lock wait exceeded ${max_wait}s. Forcibly removing stale lock."
rm -rf "$STATUS_FILE.lockdir"
fi
done
}
unlock_status() {
rmdir "$STATUS_FILE.lockdir"
}
update_status() {
local file_path="$1" lang="$2" status="$3"
lock_status
jq --arg file "$file_path" --arg lang "$lang" --arg status "$status" \
'.[$file][$lang] = $status' "$STATUS_FILE" >"$STATUS_FILE.tmp" && mv "$STATUS_FILE.tmp" "$STATUS_FILE"
unlock_status
}
# --- Translation Function ---
translate_text() {
local text="$1" lang="$2"
local retry_count=0
while [ "$retry_count" -lt "$MAX_RETRIES" ]; do
user_message="Translate the following text to $lang. Preserve all formatting exactly as in the original.
$text"
json_payload=$(jq -n \
--arg system "Translate from English to $lang. Preserve original formatting exactly." \
--arg user_message "$user_message" \
'{
"model": "gpt-4o-mini",
"messages": [
{"role": "system", "content": $system},
{"role": "user", "content": $user_message}
],
"temperature": 0.3
}')
response=$(curl -s https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d "$json_payload")
log_step "📥 Received API response."
local error_type
error_type=$(echo "$response" | jq -r '.error.type // empty')
local error_message
error_message=$(echo "$response" | jq -r '.error.message // empty')
if [ "$error_type" == "insufficient_quota" ]; then
sleep "$WAIT_TIME"
retry_count=$((retry_count + 1))
elif [[ "$error_type" == "rate_limit_reached" || "$error_type" == "server_error" || "$error_type" == "service_unavailable" ]]; then
sleep "$WAIT_TIME"
retry_count=$((retry_count + 1))
elif [ "$error_type" == "invalid_request_error" ]; then
return 1
elif [ -z "$error_type" ]; then
if ! translated_text=$(echo "$response" | jq -r '.choices[0].message.content' 2>/dev/null); then
return 1
fi
if [ "$translated_text" == "null" ] || [ -z "$translated_text" ]; then
return 1
else
translated_text=$(echo "$translated_text" | sed -e 's/^```[[:space:]]*//; s/[[:space:]]*```$//')
echo "$translated_text"
return 0
fi
else
return 1
fi
done
return 1
}
# --- Process a Single File (Sequential Version) ---
process_file() {
local src_file="$1" target_file="$2" lang="$3" rel_src="$4"
# If target file exists and is non-empty, mark status as success.
if [ -s "$target_file" ]; then
update_status "$rel_src" "$lang" "success"
return 0
fi
content=$(<"$src_file")
if [[ "$content" =~ ^[---|\+\+\+]([:space:)]*$ ]] && [[ "$content" =~ [[:space:]]*[---|\+\+\+\+]([:space:)]*$ ]]; then
front_matter=$(echo "$content" | sed -n '/^\(---\|\+\+\+\)$/,/^\(---\|\+\+\+\)$/p')
body_content=$(echo "$content" | sed -n '/^\(---\|\+\+\+\)$/,/^\(---\|\+\+\+\)$/d')
else
front_matter=""
body_content="$content"
fi
log_step "Translating [$rel_src] to $lang..."
translated_body=$(translate_text "$body_content" "$lang")
if [ $? -ne 0 ]; then
update_status "$rel_src" "$lang" "failed"
return 1
fi
mkdir -p "$(dirname "$target_file")"
if [ -n "$front_matter" ]; then
echo -e "$front_matter
$translated_body" >"$target_file"
else
echo -e "$translated_body" >"$target_file"
fi
updated_content=$(echo "$content" | sed -E 's/^retranslate:\s*true/retranslate: false/')
echo "$updated_content" >"$src_file"
update_status "$rel_src" "$lang" "success"
}
# --- Main Sequential Processing ---
ALL_SUCCESS=true
for TARGET_LANG in "${SUPPORTED_LANGUAGES[@]}"; do
log_step "Processing language: $TARGET_LANG"
TARGET_DIR="$SCRIPT_DIR/Content/$TARGET_LANG"
while IFS= read -r -d '' src_file; do
rel_src="${src_file#$SCRIPT_DIR/}"
target_file="$TARGET_DIR/${src_file#$SRC_DIR/}"
# If file is marked not to retranslate, check that target file exists and is non-empty.
if ! [[ " ${NEW_LANGUAGES[@]:-} " =~ " ${TARGET_LANG} " ]] && grep -q '^retranslate:\s*false' "$src_file"; then
if [ -s "$target_file" ]; then
update_status "$rel_src" "$TARGET_LANG" "success"
else
update_status "$rel_src" "$TARGET_LANG" "failed"
fi
continue
fi
process_file "$src_file" "$target_file" "$TARGET_LANG" "$rel_src"
done < <(find "$SRC_DIR" -type f -name "*.md" -print0)
done
log_step "Translation run completed."
end_time=$(date +%s)
duration=$((end_time - $(date +%s)))
log_step "Execution Time: $duration seconds"
if [ "$ALL_SUCCESS" = true ]; then
log_step "🎉 Translation completed successfully for all supported languages!"
else
log_step "⚠️ Translation completed with some errors."
fi
# --- Clean Up Fully Translated New Languages ---
if [ -f "$SCRIPT_DIR/translate_new_language.txt" ]; then
log_step "Cleaning up fully translated new languages..."
for lang in "${NEW_LANGUAGES[@]:-}"; do
incomplete=$(jq --arg lang "$lang" 'to_entries[] | select(.value[$lang] != null and (.value[$lang] != "success")) | .key' "$STATUS_FILE")
if [ -z "$incomplete" ]; then
log_step "All translations for new language '$lang' are marked as success. Removing from translate_new_language.txt."
sed -E -i '' "/^[[:space:]]*$lang[[:space:]]*$/d" "$SCRIPT_DIR/translate_new_language.txt"
else
log_step "Language '$lang' still has incomplete translations."
fi
done
fi
```
3. Maareynta Xaaladda Turjumaadda
Si looga hortago turjumaadyo isku mid ah oo soo noqnoqda iyo si loo raaco horumarka, waxaan isticmaalnay fayl JSON ah (translation_status.json). Script-ku wuxuu cusbooneysiiyaa faylkan kadib marka uu ka shaqeeyo dukumeenti kasta, isagoo hubinaya in kaliya nuxurka cusub ama la cusbooneysiiyey la turjumo.
4. Maareynta Khaladaadka iyo Xaddidaadaha Heerka API
Waxaan hirgelinay isku dayo marar badan iyo maareynta khaladaadka si aan ula tacaalno xaddidaadaha heerka, fashilka API, iyo arrimaha quota. Script-ku wuxuu sugaa ka hor inta uusan mar kale isku dayin haddii OpenAI API uu soo celiyo khalad sida rate_limit_reached ama service_unavailable.
5. Daabacaadda
Marka nuxurka turjuman la soo saaro, orodka hugo --minify wuxuu dhisaa website static ah oo luuqado badan leh, diyaar u ah in la daabaco.
Caqabadaha iyo Xalalka
1. Saxnaanta Turjumaadda
Inkastoo turjumaadaha OpenAI guud ahaan sax ahaayeen, qaar ka mid ah ereyada farsamada waxay u baahan karaan dib u eegis gacanta ah, laakiin annagu koox ahaan waa laba qof oo keliya, sidaas darteed waxaan rajeyneynaa waxa ugu wanaagsan. Waxaan hagaajinay prompts si aan u ilaalino macnaha iyo codka.
2. Dhibaatooyinka Qaabeynta
Mararka qaar qaabka Markdown ayaa isbeddel ku yimaada turjumaadda. Si tan loo saxo, waxaan ku darnay habka ka shaqeynta kadib si loo ilaaliyo qaabeynta.
3. Kharashka API-ga oo La Yareeyo
Si loo yareeyo kharashka, waxaan hirgelinay caching si aan uga fogaanno turjumida nuxurka aan isbeddelin.
4. Maareynta Dib-u-turjumida Si Hufan
Si dib loogu turjumo bogag gaar ah, waxaan ku darnay parameter retranslate: true oo ku jira front matter-ka. Script-ku wuxuu dib u turjumaa kaliya bogagga calaamadsan. Tani waxay noo ogolaataa inaan cusbooneysiino turjumaadaha sida loo baahdo annagoo aan dib u turjumin website-ka oo dhan.
Gabagabo
Anagoo isku daray OpenAI API iyo Hugo, waxaan si otomaatig ah u turjumnay website-keena annagoo ilaalinayna tayada iyo dabacsanaanta. Habkan wuxuu badbaadiyay waqti, hubiyay isku mid ahaansho, wuxuuna noo suurageliyay inaan si fudud u ballaarino. Haddii aad rabto inaad website-kaaga Hugo ka dhigto mid luuqado badan leh, API-ga OpenAI waa xal awood leh.