From 315e747a4c067752dfc69d3d2d6dc23f0c30d8c0 Mon Sep 17 00:00:00 2001
From: kaa <kaa@laptosh.my.domain>
Date: Wed, 3 Jul 2024 08:41:58 -0700
Subject: Public release.

---
 sift.go | 132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 132 insertions(+)
 create mode 100644 sift.go

(limited to 'sift.go')

diff --git a/sift.go b/sift.go
new file mode 100644
index 0000000..284a8fa
--- /dev/null
+++ b/sift.go
@@ -0,0 +1,132 @@
+// Generate CSV from Google Books queries.
+// authors, title, publishedDate, publisher, ISBN-13, ISBN-10, URL
+package main
+
+import (
+	"bufio"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"io/fs"
+	"log"
+	"os"
+	"strings"
+)
+
+func readFile(name string) []byte {
+	in, err := os.Open(name)
+	if err != nil {
+		log.Fatal(err)
+	}
+	defer in.Close()
+	body, err := io.ReadAll(in)
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	return body
+}
+
+func write(writer *bufio.Writer, contents string) {
+	_, err := writer.Write([]byte(contents))
+	if err != nil {
+		log.Fatal(err)
+	}
+}
+
+/* Unnecessary complication.
+Only one entry needs to be in memory at a time.
+type Entry struct {
+	authors: string
+	title: string
+	publishedDate: string
+	isbn13: string
+	isbn10: string
+	url: string
+}*/
+
+func main() {
+	// Read a list of file names, named after google books queries
+	var fullTitle, authors, publishedDate, isbn13, isbn10, url string
+
+	for _, title := range strings.Split(string(readFile("list")), "\n") {
+		if (len(title) < 3) {
+			continue
+		}
+
+		fmt.Println(title)
+
+		// For each title, create csv file
+		var out *os.File
+		_, err := os.Stat(title + ".csv")
+		if errors.Is(err, fs.ErrNotExist) {
+			//log.Print(err)
+			out, err = os.Create(title + ".csv")
+			if err != nil {
+				log.Fatal(err)
+			}
+		} else if err != nil {
+			log.Fatal(err)
+		} else {
+			out, err = os.Open(title + ".csv")
+			if err != nil {
+				log.Fatal(err)
+			}
+		}
+		defer out.Close()
+
+		outWriter := bufio.NewWriter(out)
+		//outWriter := bufio.NewWriter(os.Stdout)
+
+		// Print CSV header
+		write(outWriter, "Title, Authors, Published Date, ISBN-13, ISBN-10, URL\n")
+		defer outWriter.Flush()
+
+		// In each provided file, JSON results
+		rawJson := readFile(title)
+		var data interface{}
+		// Parse the JSON into an associative array
+		json.Unmarshal(rawJson, &data)
+		// Get through the cruft
+		m := data.(map[string]interface{})
+		for _, subm := range m["items"].([]interface{}) {
+			switch subm.(type) {
+			case map[string]interface{}:
+				m := subm.(map[string]interface{})
+				m = m["volumeInfo"].(map[string]interface{})
+				isbns := m["industryIdentifiers"].([]interface{})
+				for _, v := range isbns {
+					isbn := v.(map[string]interface{})
+					isbnText := isbn["identifier"].(string)
+					// ISBN-10 is sometimes 9 digits, ISBN-13 is always 13 digits
+					if len(isbnText) == 13 {
+						isbn13 = isbnText
+					} else {
+						isbn10 = isbnText
+					}
+				}
+
+				authorsMap := m["authors"].([]interface{})
+				for i, author := range authorsMap {
+					authorText := author.(string)
+					if i > 0 {
+						authors += " & "
+						authors += authorText
+					} else {
+						authors = authorText
+					}
+				}
+
+				fullTitle = strings.Replace(m["title"].(string), ",", "", -1)
+				if m["publishedDate"] != nil {
+					publishedDate = m["publishedDate"].(string)
+				}
+				url = m["infoLink"].(string)
+			default:
+			}
+			write(outWriter, fmt.Sprintf("%s,%s,%s,%s,%s,%s\n", fullTitle, authors, publishedDate, isbn13, isbn10, url))
+
+		}
+	}
+}
-- 
cgit v1.2.3