The open source AI code editor

package http

import (
    "io"
    "log/slog"
    "mime/multipart"
    "net/http"
    "strings"
)

type BatchItemResult struct {
    Name string `json:"name"`
    Metadata *struct {
        Format string `json:"format"`
        Width  int    `json:"width"`
        Height int    `json:"height"`
        Bytes  int    `json:"bytes"`
    } `json:"metadata,omitempty"`
    Error string `json:"error,omitempty"`
}

type BatchResponse struct {
    Results []*BatchItemResult `json:"results"`
    Count   int                `json:"count"`
    Success int                `json:"success"`
    Failed  int                `json:"failed"`
}

// handleProcessBatch processes multiple uploaded images (multipart/form-data) under the field name "files".
// It returns metadata for each image or an error per item without failing the whole batch unless the request is malformed.
func (s *Server) handleProcessBatch(w http.ResponseWriter, r *http.Request) {
    // Enforce max body size overall.
    r.Body = http.MaxBytesReader(w, r.Body, s.cfg.MaxUploadBytes)
    if ct := r.Header.Get("Content-Type"); !strings.HasPrefix(ct, "multipart/form-data") {
        s.writeJSON(w, http.StatusBadRequest, map[string]string{"error": "content type must be multipart/form-data"})
        return
    }
    if err := r.ParseMultipartForm(s.cfg.MaxUploadBytes); err != nil {
        status := http.StatusBadRequest
        if strings.Contains(err.Error(), "request body too large") {
            status = http.StatusRequestEntityTooLarge
        }
        s.writeJSON(w, status, map[string]string{"error": "invalid multipart form: " + err.Error()})
        return
    }

    // Accept files under the key "files". If absent, attempt to fallback to any file parts.
    var fileHeaders []*multipart.FileHeader
    if r.MultipartForm != nil && len(r.MultipartForm.File["files"]) > 0 {
        fileHeaders = r.MultipartForm.File["files"]
    } else if r.MultipartForm != nil {
        // Fallback: gather all files across keys.
        for _, fhs := range r.MultipartForm.File {
            fileHeaders = append(fileHeaders, fhs...)
        }
    }

    if len(fileHeaders) == 0 {
        s.writeJSON(w, http.StatusBadRequest, map[string]string{"error": "no files provided (expect key 'files')"})
        return
    }

    resp := &BatchResponse{Results: make([]*BatchItemResult, 0, len(fileHeaders))}

    for _, fh := range fileHeaders {
        item := &BatchItemResult{Name: fh.Filename}
        f, err := fh.Open()
        if err != nil {
            item.Error = "open file: " + err.Error()
            resp.Results = append(resp.Results, item)
            resp.Failed++
            continue
        }
        data, err := io.ReadAll(f)
        _ = f.Close()
        if err != nil {
            item.Error = "read file: " + err.Error()
            resp.Results = append(resp.Results, item)
            resp.Failed++
            continue
        }
        meta, err := s.proc.ExtractMetadata(data)
        if err != nil {
            item.Error = err.Error()
            resp.Results = append(resp.Results, item)
            resp.Failed++
            continue
        }
        // Copy into anonymous struct to decouple from internal type if it changes.
        item.Metadata = &struct {
            Format string `json:"format"`
            Width  int    `json:"width"`
            Height int    `json:"height"`
            Bytes  int    `json:"bytes"`
        }{Format: meta.Format, Width: meta.Width, Height: meta.Height, Bytes: meta.Bytes}
        resp.Results = append(resp.Results, item)
        resp.Success++
    }

    resp.Count = len(resp.Results)
    s.log.LogAttrs(r.Context(), slog.LevelInfo, "batch processed", slog.Int("count", resp.Count), slog.Int("success", resp.Success), slog.Int("failed", resp.Failed))
    s.writeJSON(w, http.StatusOK, resp)
}

import numpy as np
import pandas as pd

iris_data = pd.read_csv("iris_dataset.csv")

def describe(species: str) -> pd.Series:

        7
        
      
subset = data[data["species"] == species]          
subset = iris_data[iris_data["species"] == species]
if subset.empty:
raise ValueError(f"{species} missing from sample")
return subset[["petal", "sepal"]].agg(["mean", "std"]).loc["mean"]

def summary():

        13
        
      
for species in np.sort(data["species"].unique()):     
for species in np.sort(iris_data["species"].unique()):
try:
stats = describe(species)
except ValueError:
print(f"{species}: no records")
continue
print(f"{species}: petal={stats['petal']:.2f} sepal={stats['sepal']:.2f}")

if __name__ == "__main__":
summary()