commit d0f56096e8a57f3ad2c684b51fb44bca39e323b4 Author: maxwell Date: Wed Jan 15 09:04:50 2025 +0800 init diff --git a/.env b/.env new file mode 100644 index 0000000..146fd86 --- /dev/null +++ b/.env @@ -0,0 +1,4 @@ +TENCENT_SECRET_ID=AKIDwuhKk2EEF9pJdmjgV9ZozzGPL8vgXR9e +TENCENT_SECRET_KEY=Kf0Md3Uix2yiMrMk03ucAVdfVAev6DDI +GEMINI_API_KEY=AIzaSyBn6R7JWK8z58cETrHoXIbdJQ6x7QUR14o +API_KEY=1234567890 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..cad3514 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +# 腾讯手写识别接口转接 + +1. 输入图片的BASE64,返回识别结果 + +2. 使用JSON POST传输,返回JSON,符合restful风格 +3. 入参: + - 图片的BASE64,string + - Scene:场景,默认是null,可选only_hw,string + - apikey: 测试期间,设置为固定值:1234567890,string +4. 出参: + - 识别结果,string + - 成功与否,boolean + +6. 使用腾讯通用手写体识别OCR SDK进行图像识别, 使用go语言,gin框架开发; +7. 流程: + - 应用接收到POST数据以后,校验数据的合法性(json格式、base64格式等); + - 调用腾讯通用手写体识别OCR SDK进行图像识别; + - 再调用google gemini的api进行组织语言,去除可能识别的错误。使用如下prompt: + ``` + 你是一个专业的助手,负责纠正OCR识别结果中的文本。只需要输出识别结果,不需要输出任何解释。 + ``` + - 返回识别结果。 + +8. google gemini的api key:"AIzaSyBn6R7JWK8z58cETrHoXIbdJQ6x7QUR14o" +9. tencentSecretId = "AKIDwuhKk2EEF9pJdmjgV9ZozzGPL8vgXR9e",tencentSecretKey = "Kf0Md3Uix2yiMrMk03ucAVdfVAev6DDI" + +10. key存储在.env文件中,使用dotenv库进行加载。 +11. go的示例代码如下: + +```go +package main + +import ( + "fmt" + + "github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common" + "github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common/errors" + "github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common/profile" + ocr "github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/ocr/v20181119" +) + +func main() { + // 实例化一个认证对象,入参需要传入腾讯云账户 SecretId 和 SecretKey,此处还需注意密钥对的保密 + // 代码泄露可能会导致 SecretId 和 SecretKey 泄露,并威胁账号下所有资源的安全性。以下代码示例仅供参考,建议采用更安全的方式来使用密钥,请参见:https://cloud.tencent.com/document/product/1278/85305 + // 密钥可前往官网控制台 https://console.cloud.tencent.com/cam/capi 进行获取 + credential := common.NewCredential( + "SecretId", + "SecretKey", + ) + // 实例化一个client选项,可选的,没有特殊需求可以跳过 + cpf := profile.NewClientProfile() + cpf.HttpProfile.Endpoint = "ocr.tencentcloudapi.com" + // 实例化要请求产品的client对象,clientProfile是可选的 + client, _ := ocr.NewClient(credential, "", cpf) + + // 实例化一个请求对象,每个接口都会对应一个request对象 + request := ocr.NewGeneralHandwritingOCRRequest() + + rrequest.ImageBase64 = common.StringPtr("/9j/4AAQSkZJRg.....s97n//2Q==") + request.Scene = common.StringPtr("only_hw") + + // 返回的resp是一个GeneralHandwritingOCRResponse的实例,与请求对象对应 + response, err := client.GeneralHandwritingOCR(request) + if _, ok := err.(*errors.TencentCloudSDKError); ok { + fmt.Printf("An API error has returned: %s", err) + return + } + if err != nil { + panic(err) + } + // 输出json格式的字符串回包 + fmt.Printf("%s", response.ToJsonString()) +} +``` +项目结构 +``` +your-project/ +├── go.mod +├── go.sum +├── cmd/ +│ └── server/ +│ └── main.go +└── pkg/ + ├── config/ + │ └── config.go + └── handler/ + └── ocr.go + +``` \ No newline at end of file diff --git a/cmd/server/main.go b/cmd/server/main.go new file mode 100644 index 0000000..4fd60c5 --- /dev/null +++ b/cmd/server/main.go @@ -0,0 +1,36 @@ +package main + +import ( + "log" + + "github.com/gin-gonic/gin" + "tencenthw/pkg/config" + "tencenthw/pkg/handler" +) + +func main() { + // Load configuration + cfg, err := config.LoadConfig() + if err != nil { + log.Fatalf("Failed to load configuration: %v", err) + } + + // Initialize handler + ocrHandler := handler.NewOCRHandler( + cfg.TencentSecretID, + cfg.TencentSecretKey, + cfg.GeminiAPIKey, + cfg.APIKey, + ) + + // Setup Gin router + r := gin.Default() + + // Register routes + r.POST("/ocr", ocrHandler.HandleOCR) + + // Start server + if err := r.Run("localhost:8080"); err != nil { + log.Fatalf("Failed to start server: %v", err) + } +} \ No newline at end of file diff --git a/go.mod b/go.mod new file mode 100644 index 0000000..02aea84 --- /dev/null +++ b/go.mod @@ -0,0 +1,65 @@ +module tencenthw + +go 1.23.4 + +require ( + github.com/gin-gonic/gin v1.10.0 + github.com/google/generative-ai-go v0.19.0 + github.com/joho/godotenv v1.5.1 + github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common v1.0.1081 + github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/ocr v1.0.1081 + google.golang.org/api v0.216.0 +) + +require ( + cloud.google.com/go v0.115.0 // indirect + cloud.google.com/go/ai v0.8.0 // indirect + cloud.google.com/go/auth v0.13.0 // indirect + cloud.google.com/go/auth/oauth2adapt v0.2.6 // indirect + cloud.google.com/go/compute/metadata v0.6.0 // indirect + cloud.google.com/go/longrunning v0.5.7 // indirect + github.com/bytedance/sonic v1.11.6 // indirect + github.com/bytedance/sonic/loader v0.1.1 // indirect + github.com/cloudwego/base64x v0.1.4 // indirect + github.com/cloudwego/iasm v0.2.0 // indirect + github.com/felixge/httpsnoop v1.0.4 // indirect + github.com/gabriel-vasile/mimetype v1.4.3 // indirect + github.com/gin-contrib/sse v0.1.0 // indirect + github.com/go-logr/logr v1.4.2 // indirect + github.com/go-logr/stdr v1.2.2 // indirect + github.com/go-playground/locales v0.14.1 // indirect + github.com/go-playground/universal-translator v0.18.1 // indirect + github.com/go-playground/validator/v10 v10.20.0 // indirect + github.com/goccy/go-json v0.10.2 // indirect + github.com/google/s2a-go v0.1.8 // indirect + github.com/google/uuid v1.6.0 // indirect + github.com/googleapis/enterprise-certificate-proxy v0.3.4 // indirect + github.com/googleapis/gax-go/v2 v2.14.1 // indirect + github.com/json-iterator/go v1.1.12 // indirect + github.com/klauspost/cpuid/v2 v2.2.7 // indirect + github.com/leodido/go-urn v1.4.0 // indirect + github.com/mattn/go-isatty v0.0.20 // indirect + github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect + github.com/modern-go/reflect2 v1.0.2 // indirect + github.com/pelletier/go-toml/v2 v2.2.2 // indirect + github.com/twitchyliquid64/golang-asm v0.15.1 // indirect + github.com/ugorji/go/codec v1.2.12 // indirect + go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.54.0 // indirect + go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0 // indirect + go.opentelemetry.io/otel v1.31.0 // indirect + go.opentelemetry.io/otel/metric v1.31.0 // indirect + go.opentelemetry.io/otel/trace v1.31.0 // indirect + golang.org/x/arch v0.8.0 // indirect + golang.org/x/crypto v0.31.0 // indirect + golang.org/x/net v0.33.0 // indirect + golang.org/x/oauth2 v0.25.0 // indirect + golang.org/x/sync v0.10.0 // indirect + golang.org/x/sys v0.28.0 // indirect + golang.org/x/text v0.21.0 // indirect + golang.org/x/time v0.9.0 // indirect + google.golang.org/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576 // indirect + google.golang.org/genproto/googleapis/rpc v0.0.0-20250102185135-69823020774d // indirect + google.golang.org/grpc v1.69.2 // indirect + google.golang.org/protobuf v1.36.1 // indirect + gopkg.in/yaml.v3 v3.0.1 // indirect +) diff --git a/go.sum b/go.sum new file mode 100644 index 0000000..1cc14d2 --- /dev/null +++ b/go.sum @@ -0,0 +1,152 @@ +cloud.google.com/go v0.115.0 h1:CnFSK6Xo3lDYRoBKEcAtia6VSC837/ZkJuRduSFnr14= +cloud.google.com/go v0.115.0/go.mod h1:8jIM5vVgoAEoiVxQ/O4BFTfHqulPZgs/ufEzMcFMdWU= +cloud.google.com/go/ai v0.8.0 h1:rXUEz8Wp2OlrM8r1bfmpF2+VKqc1VJpafE3HgzRnD/w= +cloud.google.com/go/ai v0.8.0/go.mod h1:t3Dfk4cM61sytiggo2UyGsDVW3RF1qGZaUKDrZFyqkE= +cloud.google.com/go/auth v0.13.0 h1:8Fu8TZy167JkW8Tj3q7dIkr2v4cndv41ouecJx0PAHs= +cloud.google.com/go/auth v0.13.0/go.mod h1:COOjD9gwfKNKz+IIduatIhYJQIc0mG3H102r/EMxX6Q= +cloud.google.com/go/auth/oauth2adapt v0.2.6 h1:V6a6XDu2lTwPZWOawrAa9HUK+DB2zfJyTuciBG5hFkU= +cloud.google.com/go/auth/oauth2adapt v0.2.6/go.mod h1:AlmsELtlEBnaNTL7jCj8VQFLy6mbZv0s4Q7NGBeQ5E8= +cloud.google.com/go/compute/metadata v0.6.0 h1:A6hENjEsCDtC1k8byVsgwvVcioamEHvZ4j01OwKxG9I= +cloud.google.com/go/compute/metadata v0.6.0/go.mod h1:FjyFAW1MW0C203CEOMDTu3Dk1FlqW3Rga40jzHL4hfg= +cloud.google.com/go/longrunning v0.5.7 h1:WLbHekDbjK1fVFD3ibpFFVoyizlLRl73I7YKuAKilhU= +cloud.google.com/go/longrunning v0.5.7/go.mod h1:8GClkudohy1Fxm3owmBGid8W0pSgodEMwEAztp38Xng= +github.com/bytedance/sonic v1.11.6 h1:oUp34TzMlL+OY1OUWxHqsdkgC/Zfc85zGqw9siXjrc0= +github.com/bytedance/sonic v1.11.6/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4= +github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM= +github.com/bytedance/sonic/loader v0.1.1/go.mod h1:ncP89zfokxS5LZrJxl5z0UJcsk4M4yY2JpfqGeCtNLU= +github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/0Y= +github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w= +github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg= +github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY= +github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= +github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg= +github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U= +github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0= +github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk= +github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE= +github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI= +github.com/gin-gonic/gin v1.10.0 h1:nTuyha1TYqgedzytsKYqna+DfLos46nTv2ygFy86HFU= +github.com/gin-gonic/gin v1.10.0/go.mod h1:4PMNQiOhvDRa013RKVbsiNwoyezlm2rm0uX/T7kzp5Y= +github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A= +github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY= +github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY= +github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag= +github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE= +github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s= +github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4= +github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA= +github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY= +github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY= +github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY= +github.com/go-playground/validator/v10 v10.20.0 h1:K9ISHbSaI0lyB2eWMPJo+kOS/FBExVwjEviJTixqxL8= +github.com/go-playground/validator/v10 v10.20.0/go.mod h1:dbuPbCMFw/DrkbEynArYaCwl3amGuJotoKCe95atGMM= +github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU= +github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I= +github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek= +github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps= +github.com/google/generative-ai-go v0.19.0 h1:R71szggh8wHMCUlEMsW2A/3T+5LdEIkiaHSYgSpUgdg= +github.com/google/generative-ai-go v0.19.0/go.mod h1:JYolL13VG7j79kM5BtHz4qwONHkeJQzOCkKXnpqtS/E= +github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI= +github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= +github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg= +github.com/google/s2a-go v0.1.8 h1:zZDs9gcbt9ZPLV0ndSyQk6Kacx2g/X+SKYovpnz3SMM= +github.com/google/s2a-go v0.1.8/go.mod h1:6iNWHTpQ+nfNRN5E00MSdfDwVesa8hhS32PhPO8deJA= +github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0= +github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= +github.com/googleapis/enterprise-certificate-proxy v0.3.4 h1:XYIDZApgAnrN1c855gTgghdIA6Stxb52D5RnLI1SLyw= +github.com/googleapis/enterprise-certificate-proxy v0.3.4/go.mod h1:YKe7cfqYXjKGpGvmSg28/fFvhNzinZQm8DGnaburhGA= +github.com/googleapis/gax-go/v2 v2.14.1 h1:hb0FFeiPaQskmvakKu5EbCbpntQn48jyHuvrkurSS/Q= +github.com/googleapis/gax-go/v2 v2.14.1/go.mod h1:Hb/NubMaVM88SrNkvl8X/o8XWwDJEPqouaLeN2IUxoA= +github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0= +github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4= +github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM= +github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo= +github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg= +github.com/klauspost/cpuid/v2 v2.2.7 h1:ZWSB3igEs+d0qvnxR/ZBzXVmxkgt8DdzP6m9pfuVLDM= +github.com/klauspost/cpuid/v2 v2.2.7/go.mod h1:Lcz8mBdAVJIBVzewtcLocK12l3Y+JytZYpaMropDUws= +github.com/knz/go-libedit v1.10.1/go.mod h1:MZTVkCWyz0oBc7JOWP3wNAzd002ZbM/5hgShxwh4x8M= +github.com/leodido/go-urn v1.4.0 h1:WT9HwE9SGECu3lg4d/dIA+jxlljEa1/ffXKmRjqdmIQ= +github.com/leodido/go-urn v1.4.0/go.mod h1:bvxc+MVxLKB4z00jd1z+Dvzr47oO32F/QSNjSBOlFxI= +github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY= +github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y= +github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= +github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg= +github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= +github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M= +github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk= +github.com/pelletier/go-toml/v2 v2.2.2 h1:aYUidT7k73Pcl9nb2gScu7NSrKCSHIDE89b3+6Wq+LM= +github.com/pelletier/go-toml/v2 v2.2.2/go.mod h1:1t835xjRzz80PqgE6HHgN2JOsmgYu/h4qDAS4n929Rs= +github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= +github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= +github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw= +github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo= +github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA= +github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= +github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= +github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= +github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU= +github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4= +github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo= +github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg= +github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY= +github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common v1.0.1081 h1:se2XGbNPtL4Q5ur8XzuEdoGtvhIxlSQSLzIrr/NcgwM= +github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common v1.0.1081/go.mod h1:r5r4xbfxSaeR04b166HGsBa/R4U3SueirEUpXGuw+Q0= +github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/ocr v1.0.1081 h1:LQC0VlqApB75Eep1953nLTrGlm0OobmuTbCw1MO7oUg= +github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/ocr v1.0.1081/go.mod h1:SqoMs+r1/bBKrsCiwEOklYKLM0Bog+PouQ68H8hjRf0= +github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI= +github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08= +github.com/ugorji/go/codec v1.2.12 h1:9LC83zGrHhuUA9l16C9AHXAqEV/2wBQ4nkvumAE65EE= +github.com/ugorji/go/codec v1.2.12/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg= +go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.54.0 h1:r6I7RJCN86bpD/FQwedZ0vSixDpwuWREjW9oRMsmqDc= +go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.54.0/go.mod h1:B9yO6b04uB80CzjedvewuqDhxJxi11s7/GtiGa8bAjI= +go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0 h1:TT4fX+nBOA/+LUkobKGW1ydGcn+G3vRw9+g5HwCphpk= +go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0/go.mod h1:L7UH0GbB0p47T4Rri3uHjbpCFYrVrwc1I25QhNPiGK8= +go.opentelemetry.io/otel v1.31.0 h1:NsJcKPIW0D0H3NgzPDHmo0WW6SptzPdqg/L1zsIm2hY= +go.opentelemetry.io/otel v1.31.0/go.mod h1:O0C14Yl9FgkjqcCZAsE053C13OaddMYr/hz6clDkEJE= +go.opentelemetry.io/otel/metric v1.31.0 h1:FSErL0ATQAmYHUIzSezZibnyVlft1ybhy4ozRPcF2fE= +go.opentelemetry.io/otel/metric v1.31.0/go.mod h1:C3dEloVbLuYoX41KpmAhOqNriGbA+qqH6PQ5E5mUfnY= +go.opentelemetry.io/otel/sdk v1.31.0 h1:xLY3abVHYZ5HSfOg3l2E5LUj2Cwva5Y7yGxnSW9H5Gk= +go.opentelemetry.io/otel/sdk v1.31.0/go.mod h1:TfRbMdhvxIIr/B2N2LQW2S5v9m3gOQ/08KsbbO5BPT0= +go.opentelemetry.io/otel/sdk/metric v1.31.0 h1:i9hxxLJF/9kkvfHppyLL55aW7iIJz4JjxTeYusH7zMc= +go.opentelemetry.io/otel/sdk/metric v1.31.0/go.mod h1:CRInTMVvNhUKgSAMbKyTMxqOBC0zgyxzW55lZzX43Y8= +go.opentelemetry.io/otel/trace v1.31.0 h1:ffjsj1aRouKewfr85U2aGagJ46+MvodynlQ1HYdmJys= +go.opentelemetry.io/otel/trace v1.31.0/go.mod h1:TXZkRk7SM2ZQLtR6eoAWQFIHPvzQ06FJAsO1tJg480A= +golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8= +golang.org/x/arch v0.8.0 h1:3wRIsP3pM4yUptoR96otTUOXI367OS0+c9eeRi9doIc= +golang.org/x/arch v0.8.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys= +golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U= +golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk= +golang.org/x/net v0.33.0 h1:74SYHlV8BIgHIFC/LrYkOGIwL19eTYXQ5wc6TBuO36I= +golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4= +golang.org/x/oauth2 v0.25.0 h1:CY4y7XT9v0cRI9oupztF8AgiIu99L/ksR/Xp/6jrZ70= +golang.org/x/oauth2 v0.25.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI= +golang.org/x/sync v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ= +golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= +golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA= +golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo= +golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ= +golang.org/x/time v0.9.0 h1:EsRrnYcQiGH+5FfbgvV4AP7qEZstoyrHB0DzarOQ4ZY= +golang.org/x/time v0.9.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM= +google.golang.org/api v0.216.0 h1:xnEHy+xWFrtYInWPy8OdGFsyIfWJjtVnO39g7pz2BFY= +google.golang.org/api v0.216.0/go.mod h1:K9wzQMvWi47Z9IU7OgdOofvZuw75Ge3PPITImZR/UyI= +google.golang.org/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576 h1:CkkIfIt50+lT6NHAVoRYEyAvQGFM7xEwXUUywFvEb3Q= +google.golang.org/genproto/googleapis/api v0.0.0-20241209162323-e6fa225c2576/go.mod h1:1R3kvZ1dtP3+4p4d3G8uJ8rFk/fWlScl38vanWACI08= +google.golang.org/genproto/googleapis/rpc v0.0.0-20250102185135-69823020774d h1:xJJRGY7TJcvIlpSrN3K6LAWgNFUILlO+OMAqtg9aqnw= +google.golang.org/genproto/googleapis/rpc v0.0.0-20250102185135-69823020774d/go.mod h1:3ENsm/5D1mzDyhpzeRi1NR784I0BcofWBoSc5QqqMK4= +google.golang.org/grpc v1.69.2 h1:U3S9QEtbXC0bYNvRtcoklF3xGtLViumSYxWykJS+7AU= +google.golang.org/grpc v1.69.2/go.mod h1:vyjdE6jLBI76dgpDojsFGNaHlxdjXN9ghpnd2o7JGZ4= +google.golang.org/protobuf v1.36.1 h1:yBPeRvTftaleIgM3PZ/WBIZ7XM/eEYAaEyCwvyjq/gk= +google.golang.org/protobuf v1.36.1/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE= +gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM= +gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= +gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= +gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= +nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50= +rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4= diff --git a/hwserver b/hwserver new file mode 100755 index 0000000..4e1bad9 Binary files /dev/null and b/hwserver differ diff --git a/pkg/config/config.go b/pkg/config/config.go new file mode 100644 index 0000000..29cf025 --- /dev/null +++ b/pkg/config/config.go @@ -0,0 +1,26 @@ +package config + +import ( + "github.com/joho/godotenv" + "os" +) + +type Config struct { + TencentSecretID string + TencentSecretKey string + GeminiAPIKey string + APIKey string +} + +func LoadConfig() (*Config, error) { + if err := godotenv.Load(); err != nil { + return nil, err + } + + return &Config{ + TencentSecretID: os.Getenv("TENCENT_SECRET_ID"), + TencentSecretKey: os.Getenv("TENCENT_SECRET_KEY"), + GeminiAPIKey: os.Getenv("GEMINI_API_KEY"), + APIKey: os.Getenv("API_KEY"), + }, nil +} \ No newline at end of file diff --git a/pkg/handler/ocr.go b/pkg/handler/ocr.go new file mode 100644 index 0000000..bbf9be0 --- /dev/null +++ b/pkg/handler/ocr.go @@ -0,0 +1,166 @@ +package handler + +import ( + "encoding/base64" + "net/http" + "strings" + + "github.com/gin-gonic/gin" + "github.com/google/generative-ai-go/genai" + "github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common" + "github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common/profile" + ocr "github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/ocr/v20181119" + "google.golang.org/api/option" +) + +type OCRHandler struct { + tencentSecretID string + tencentSecretKey string + geminiAPIKey string + apiKey string +} + +type OCRRequest struct { + ImageBase64 string `json:"image_base64"` + ImageURL string `json:"image_url"` + Scene string `json:"scene"` + APIKey string `json:"apikey" binding:"required"` +} + +type OCRResponse struct { + OriginalText string `json:"original_text"` + Result string `json:"result"` + Success bool `json:"success"` +} + +func NewOCRHandler(tencentSecretID, tencentSecretKey, geminiAPIKey, apiKey string) *OCRHandler { + return &OCRHandler{ + tencentSecretID: tencentSecretID, + tencentSecretKey: tencentSecretKey, + geminiAPIKey: geminiAPIKey, + apiKey: apiKey, + } +} + +func (h *OCRHandler) HandleOCR(c *gin.Context) { + var req OCRRequest + if err := c.ShouldBindJSON(&req); err != nil { + c.JSON(http.StatusBadRequest, OCRResponse{ + Success: false, + Result: "Invalid request format", + }) + return + } + + // Validate API key + if req.APIKey != h.apiKey { + c.JSON(http.StatusUnauthorized, OCRResponse{ + Success: false, + Result: "Invalid API key", + }) + return + } + + // Validate that at least one of ImageURL or ImageBase64 is provided + if req.ImageURL == "" && req.ImageBase64 == "" { + c.JSON(http.StatusBadRequest, OCRResponse{ + Success: false, + Result: "Either image_url or image_base64 must be provided", + }) + return + } + + // Initialize Tencent Cloud client + credential := common.NewCredential(h.tencentSecretID, h.tencentSecretKey) + cpf := profile.NewClientProfile() + cpf.HttpProfile.Endpoint = "ocr.tencentcloudapi.com" + client, err := ocr.NewClient(credential, "", cpf) + if err != nil { + c.JSON(http.StatusInternalServerError, OCRResponse{ + Success: false, + Result: "Failed to initialize OCR client", + }) + return + } + + // Create OCR request + request := ocr.NewGeneralHandwritingOCRRequest() + + // Prioritize ImageURL if both are provided + if req.ImageURL != "" { + request.ImageUrl = common.StringPtr(req.ImageURL) + } else { + // Remove base64 prefix if exists + imageBase64 := req.ImageBase64 + if idx := strings.Index(imageBase64, "base64,"); idx != -1 { + imageBase64 = imageBase64[idx+7:] // 7 is the length of "base64," + } + + // Validate base64 + if _, err := base64.StdEncoding.DecodeString(imageBase64); err != nil { + c.JSON(http.StatusBadRequest, OCRResponse{ + Success: false, + Result: "Invalid base64 image", + }) + return + } + request.ImageBase64 = common.StringPtr(imageBase64) + } + + if req.Scene != "" { + request.Scene = common.StringPtr(req.Scene) + } + + // Perform OCR + response, err := client.GeneralHandwritingOCR(request) + if err != nil { + c.JSON(http.StatusInternalServerError, OCRResponse{ + Success: false, + Result: "OCR processing failed", + }) + return + } + + // Extract text from OCR response + var ocrText string + for _, textDetection := range response.Response.TextDetections { + ocrText += *textDetection.DetectedText + "\n" + } + + // Process with Gemini + ctx := c.Request.Context() + client2, err := genai.NewClient(ctx, option.WithAPIKey(h.geminiAPIKey)) + if err != nil { + c.JSON(http.StatusInternalServerError, OCRResponse{ + Success: false, + Result: "Failed to initialize Gemini client", + }) + return + } + defer client2.Close() + + model := client2.GenerativeModel("gemini-2.0-flash-exp") + prompt := "你是一个专业的助手,负责纠正OCR识别结果中的文本。只需要输出识别结果,不需要输出任何解释。\n\n" + ocrText + resp, err := model.GenerateContent(ctx, genai.Text(prompt)) + if err != nil { + c.JSON(http.StatusInternalServerError, OCRResponse{ + Success: false, + Result: "Text processing failed", + }) + return + } + + // Get the processed text from Gemini response + processedText := "" + if len(resp.Candidates) > 0 && len(resp.Candidates[0].Content.Parts) > 0 { + if textPart, ok := resp.Candidates[0].Content.Parts[0].(genai.Text); ok { + processedText = string(textPart) + } + } + + c.JSON(http.StatusOK, OCRResponse{ + Success: true, + OriginalText: ocrText, + Result: processedText, + }) +} \ No newline at end of file