@ca-plant-list/ca-plant-list 0.4.18 → 0.4.20

package/lib/tools/rpi.js

@@ -12,10 +12,10 @@ class RPI {
 
     /**
      * @param {string} toolsDataDir
-     * @param {Taxa} taxa
-     * @param {Config} config
+     * @param {import("../taxa.js").Taxa} taxa
+     * @param {import("../config.js").Config} config
      * @param {import("../exceptions.js").Exceptions} exceptions
-     * @param {ErrorLog} errorLog
+     * @param {import("../errorlog.js").ErrorLog} errorLog
      */
     static async analyze(toolsDataDir, taxa, config, exceptions, errorLog) {
         /**
@@ -202,11 +202,10 @@ class RPI {
     }
 
     /**
-     *
-     * @param {Taxa} taxa
-     * @param {Config} config
+     * @param {import("../taxa.js").Taxa} taxa
+     * @param {import("../config.js").Config} config
      * @param {import("../exceptions.js").Exceptions} exceptions
-     * @param {ErrorLog} errorLog
+     * @param {import("../errorlog.js").ErrorLog} errorLog
      */
     static #checkExceptions(taxa, config, exceptions, errorLog) {
         const countyCodes = config.getCountyCodes();
@@ -367,9 +366,9 @@ class RPI {
 
     /**
      * @param {string} toolsDataDir
-     * @param {Taxa} taxa
+     * @param {import("../taxa.js").Taxa} taxa
      * @param {import("../exceptions.js").Exceptions} exceptions
-     * @param {ErrorLog} errorLog
+     * @param {import("../errorlog.js").ErrorLog} errorLog
      */
     static async #scrape(toolsDataDir, taxa, exceptions, errorLog) {
         const toolsDataPath = toolsDataDir + "/rpi";

package/lib/tools/supplementaltext.js

@@ -0,0 +1,43 @@
+import { Files } from "../files.js";
+
+const VALID_EXTENSIONS = new Set(["md", "footer.md"]);
+
+export class SupplementalText {
+    /**
+     *
+     * @param {import("../taxa.js").Taxa} taxa
+     * @param {import("../errorlog.js").ErrorLog} errorLog
+     */
+    static analyze(taxa, errorLog) {
+        /**
+         * @param {string} fileName
+         */
+        function fileNameToTaxonName(fileName) {
+            const parts = fileName.split(".");
+            const ext = parts.slice(1).join(".");
+            const taxonName = parts[0]
+                .replace("-", " ")
+                .replace("-var-", " var. ")
+                .replace("-subsp-", " subsp. ");
+            return { taxonName: taxonName, ext: ext };
+        }
+
+        const dirName = "data/text";
+
+        if (!Files.isDir(dirName)) {
+            return;
+        }
+
+        const entries = Files.getDirEntries(dirName);
+        for (const entry of entries) {
+            const parsed = fileNameToTaxonName(entry);
+            const taxon = taxa.getTaxon(parsed.taxonName);
+            if (!taxon) {
+                errorLog.log(dirName + "/" + entry, "not found in taxa.csv");
+            }
+            if (!VALID_EXTENSIONS.has(parsed.ext)) {
+                errorLog.log(dirName + "/" + entry, "has invalid extension");
+            }
+        }
+    }
+}

package/lib/tools/taxacsv.js

@@ -4,7 +4,7 @@ import { CSV } from "../csv.js";
 export class TaxaCSV {
     #filePath;
     #headers;
-    /** @type {TaxonData[]} */
+    /** @type {import("../index.js").TaxonData[]} */
     #taxa;
 
     /**
@@ -19,7 +19,7 @@ export class TaxaCSV {
     }
 
     /**
-     * @returns {TaxonData[]}
+     * @returns {import("../index.js").TaxonData[]}
      */
     getTaxa() {
         return this.#taxa;

package/lib/utils/inat-tools.js

@@ -1,10 +1,47 @@
 import { ProgressMeter } from "../progressmeter.js";
 import { chunk, sleep } from "../util.js";
 
+/**
+  @typedef {"cc-by-nc-sa"
+    | "cc-by-nc"
+    | "cc-by-nc-nd"
+    | "cc-by"
+    | "cc-by-sa"
+    | "cc-by-nd"
+    | "pd"
+    | "gdfl"
+    | "cc0"} InatLicenseCode
+  @typedef {{
+    id: string;
+    ext: string;
+    licenseCode: string;
+    attrName: string | undefined;
+}} InatPhotoInfo
+ @typedef {{
+    id: number;
+    attribution: string;
+    license_code: InatLicenseCode;
+    medium_url?: string;
+    url?: string;
+}} InatApiPhoto
+ @typedef {{
+    id: number;
+    taxon_photos: {
+        photo: InatApiPhoto;
+    }[];
+}} InatApiTaxon
+ @typedef {{
+    name: string;
+    id: number;
+    ext: string;
+    licenseCode: InatLicenseCode;
+    attrName: string;
+    }} InatCsvPhoto
+ */
 const ALLOWED_LICENSE_CODES = ["cc0", "cc-by", "cc-by-nc"];
 
 /**
- * @param {Taxon[]} taxa
+ * @param {import("../taxon.js").Taxon[]} taxa
  * @return {Promise<InatApiTaxon[]>}
  */
 async function fetchInatTaxa(taxa) {
@@ -20,7 +57,7 @@ async function fetchInatTaxa(taxa) {
 }
 
 /**
- * @param {Taxon[]} taxaToUpdate
+ * @param {import("../taxon.js").Taxon[]} taxaToUpdate
  * @returns {Promise<Map<string,InatPhotoInfo[]>>}
  */
 export async function getTaxonPhotos(taxaToUpdate) {

package/lib/web/glossarypages.js

@@ -10,7 +10,7 @@ class GlossaryPages {
     #glossary;
 
     /**
-     * @param {SiteGenerator} siteGenerator
+     * @param {import("../sitegenerator.js").SiteGenerator} siteGenerator
      */
     constructor(siteGenerator) {
         this.#siteGenerator = siteGenerator;
@@ -18,7 +18,7 @@ class GlossaryPages {
     }
 
     /**
-     * @param {GlossaryEntry} entry
+     * @param {import("../plants/glossary.js").GlossaryEntry} entry
      */
     #generateEntryPage(entry) {
         const title = entry.getTermName();
@@ -29,7 +29,7 @@ class GlossaryPages {
         this.#siteGenerator.writeTemplate(
             html,
             { title: title },
-            Files.join(ENTRY_DIR, title + ".html")
+            Files.join(ENTRY_DIR, title + ".html"),
         );
     }
 
@@ -50,8 +50,8 @@ class GlossaryPages {
             links.push(
                 HTML.getLink(
                     Files.join(ENTRY_DIR, entry.getHTMLFileName()),
-                    entry.getTermName()
-                )
+                    entry.getTermName(),
+                ),
             );
         }
         let html = HTML.wrap("h1", "Glossary");
@@ -59,7 +59,7 @@ class GlossaryPages {
         this.#siteGenerator.writeTemplate(
             html,
             { title: "Glossary" },
-            "glossary.html"
+            "glossary.html",
         );
     }
 

package/lib/web/pagetaxon.js

@@ -11,8 +11,8 @@ class PageTaxon extends GenericPage {
 
     /**
      * @param {string} outputDir
-     * @param {Config} config
-     * @param {Taxon} taxon
+     * @param {import("../config.js").Config} config
+     * @param {import("../taxon.js").Taxon} taxon
      */
     constructor(outputDir, config, taxon) {
         super(outputDir, taxon.getName(), taxon.getBaseFileName());
@@ -189,7 +189,7 @@ class PageTaxon extends GenericPage {
 
         html += HTMLTaxon.getFooterHTML(this.#taxon);
 
-        const photos = this.#taxon.getPhotos().slice( 0, 5 );
+        const photos = this.#taxon.getPhotos().slice(0, 5);
         if (photos.length > 0) {
             let photosHtml = "";
             for (const photo of photos) {
@@ -202,9 +202,7 @@ class PageTaxon extends GenericPage {
               />
             </a>
             <figcaption>
-              ${photo.rights === "CC0" ? "By" : "(c)"}
-              ${photo.rightsHolder}
-              ${photo.rights && `(${photo.rights})`}
+              ${photo.getAttribution()}
             </figcaption>
           </figure>
         `;

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@ca-plant-list/ca-plant-list",
-    "version": "0.4.18",
+    "version": "0.4.20",
     "description": "Tools to create Jekyll files for a website listing plants in an area of California.",
     "license": "MIT",
     "repository": {
@@ -14,16 +14,16 @@
         "ebook",
         "jekyll",
         "lib",
-        "scripts",
-        "types"
+        "scripts"
     ],
     "exports": {
         ".": "./lib/index.js"
     },
     "types": "./lib/index.d.ts",
     "scripts": {
-        "check": "npm run eslint && npm run tsc",
+        "check": "npm run eslint && npm run tsc && npm run jest",
         "eslint": "npx eslint",
+        "jest": "node --experimental-vm-modules node_modules/jest/bin/jest.js tests",
         "prettier": "npx prettier -l .",
         "tsc": "npx tsc"
     },
@@ -35,7 +35,7 @@
         "inatobsphotos": "scripts/inatobsphotos.js"
     },
     "dependencies": {
-        "@htmltools/scrape": "^0.1.0",
+        "@htmltools/scrape": "^0.1.1",
         "archiver": "^5.3.1",
         "cli-progress": "^3.12.0",
         "commander": "^12.1.0",
@@ -51,11 +51,13 @@
     "devDependencies": {
         "@types/archiver": "^6.0.2",
         "@types/cli-progress": "^3.11.6",
+        "@types/jest": "^29.5.14",
         "@types/markdown-it": "^14.1.2",
-        "@types/node": "^22.10.3",
+        "@types/node": "^22.10.7",
         "@types/unzipper": "^0.10.9",
-        "eslint": "^9.17.0",
+        "eslint": "^9.18.0",
+        "jest": "^29.7.0",
         "prettier": "^3.4.2",
-        "typescript": "^5.7.2"
+        "typescript": "^5.7.3"
     }
 }

package/scripts/cpl-photos.js

@@ -129,7 +129,7 @@ async function getTaxa(options) {
 }
 
 /**
- * @returns {Map<string,InatPhotoInfo[]>}
+ * @returns {Map<string,import("../lib/utils/inat-tools.js").InatPhotoInfo[]>}
  */
 function readPhotos() {
     const photosFileName = `./data/${PHOTO_FILE_NAME}`;
@@ -140,7 +140,7 @@ function readPhotos() {
     /** @type {Map<string,{id:string,ext:string,licenseCode:string,attrName:string}[]>} */
     const taxonPhotos = new Map();
 
-    /** @type {InatCsvPhoto[]} */
+    /** @type {import("../lib/utils/inat-tools.js").InatCsvPhoto[]} */
     // @ts-ignore
     const csvPhotos = CSV.readFile(photosFileName);
     for (const csvPhoto of csvPhotos) {

package/scripts/cpl-tools.js

@@ -11,6 +11,8 @@ import { JepsonEFlora } from "../lib/tools/jepsoneflora.js";
 import { RPI } from "../lib/tools/rpi.js";
 import { Config } from "../lib/config.js";
 import { Taxa } from "../lib/taxa.js";
+import { SupplementalText } from "../lib/tools/supplementaltext.js";
+import { JepsonFamilies } from "../lib/tools/jepsonfamilies.js";
 
 const TOOLS = {
     CALFLORA: "calflora",
@@ -58,9 +60,11 @@ async function build(program, options) {
             case TOOLS.CALFLORA:
                 await Calflora.analyze(
                     TOOLS_DATA_DIR,
+                    options.datadir,
                     taxa,
                     exceptions,
                     errorLog,
+                    !!options.update,
                 );
                 break;
             case TOOLS.CALSCAPE:
@@ -86,11 +90,15 @@ async function build(program, options) {
                 break;
             case TOOLS.JEPSON_EFLORA: {
                 const eflora = new JepsonEFlora(TOOLS_DATA_DIR, taxa, errorLog);
-                await eflora.analyze(exceptions, !!options.update);
+                await eflora.analyze(
+                    options.datadir,
+                    exceptions,
+                    !!options.update,
+                );
                 break;
             }
             case TOOLS.JEPSON_FAM:
-                // await JepsonFamilies.build(TOOLS_DATA_DIR, options.outputdir);
+                await JepsonFamilies.build(TOOLS_DATA_DIR, "./data");
                 break;
             case TOOLS.RPI:
                 await RPI.analyze(
@@ -102,7 +110,7 @@ async function build(program, options) {
                 );
                 break;
             case TOOLS.TEXT:
-                // SupplementalText.analyze(taxa, errorLog);
+                SupplementalText.analyze(taxa, errorLog);
                 break;
             default:
                 console.log("unrecognized tool: " + tool);

package/scripts/inatobsphotos.js

@@ -9,6 +9,15 @@ import { Program } from "../lib/program.js";
 import { Taxa } from "../lib/taxa.js";
 import { sleep } from "../lib/util.js";
 
+/**
+ * @typedef {{
+    observation_photos: {
+        photo: import("../lib/utils/inat-tools.js").InatApiPhoto;
+    }[];
+}} InatApiObservation
+ @typedef {import("../lib/program.js").CommandLineOptions &{filename?:string,inatObsQuery?:string}} InatObsPhotosCommandLineOptions
+ */
+
 // While I'm guessing the products of this data will be non-commercial, it's
 // not clear how they'll be licensed so the ShareAlike clause is out, and
 // they'll probably be derivative works so the "No Derivatives" clause should
@@ -18,7 +27,7 @@ const ALLOWED_LICENSE_CODES = ["cc0", "cc-by", "cc-by-nc"];
 const DEFAULT_FILENAME = "inatobsphotos.csv";
 
 /**
- * @param {Taxon} taxon
+ * @param {import("../lib/taxon.js").Taxon} taxon
  * @param {InatObsPhotosCommandLineOptions} options
  * @return {Promise<InatApiObservation[]>}
  */

package/scripts/inattaxonphotos.js

@@ -10,24 +10,26 @@ import { Program } from "../lib/program.js";
 import { Taxa } from "../lib/taxa.js";
 import { chunk, sleep } from "../lib/util.js";
 
+/**
+ * @typedef {import("../lib/program.js").CommandLineOptions & {filename?:string}} InatTaxonPhotosCommandLineOptions
+ */
+
 // While I'm guessing the products of this data will be non-commercial, it's
 // not clear how they'll be licensed so the ShareAlike clause is out, and
 // they'll probably be derivative works so the "No Derivatives" clause should
 // be respected.
-const ALLOWED_LICENSE_CODES = [
-    "cc0", "cc-by", "cc-by-nc"
-];
+const ALLOWED_LICENSE_CODES = ["cc0", "cc-by", "cc-by-nc"];
 
 const DEFAULT_FILENAME = "inattaxonphotos.csv";
 
 /**
- * @param {Taxon[]} taxa
- * @return {Promise<InatApiTaxon[]>}
+ * @param {import("../lib/taxon.js").Taxon[]} taxa
+ * @return {Promise<import("../lib/utils/inat-tools.js").InatApiTaxon[]>}
  */
-async function fetchInatTaxa( taxa ) {
-    const inatTaxonIDs = taxa.map( taxon => taxon.getINatID( ) ).filter( Boolean );
-    const url = `https://api.inaturalist.org/v2/taxa/${inatTaxonIDs.join( "," )}?fields=(taxon_photos:(photo:(medium_url:!t,attribution:!t,license_code:!t)))`;
-    const resp = await fetch( url );
+async function fetchInatTaxa(taxa) {
+    const inatTaxonIDs = taxa.map((taxon) => taxon.getINatID()).filter(Boolean);
+    const url = `https://api.inaturalist.org/v2/taxa/${inatTaxonIDs.join(",")}?fields=(taxon_photos:(photo:(medium_url:!t,attribution:!t,license_code:!t)))`;
+    const resp = await fetch(url);
     if (!resp.ok) {
         const error = await resp.text();
         throw new Error(`Failed to fetch taxa from iNat: ${error}`);
@@ -39,74 +41,74 @@ async function fetchInatTaxa( taxa ) {
 /**
  * @param {InatTaxonPhotosCommandLineOptions} options
  */
-async function getTaxonPhotos( options ) {
+async function getTaxonPhotos(options) {
     const errorLog = new ErrorLog(options.outputdir + "/errors.tsv");
     const taxa = new Taxa(
         Program.getIncludeList(options.datadir),
         errorLog,
-        false
+        false,
     );
-    const targetTaxa = taxa.getTaxonList( );
+    const targetTaxa = taxa.getTaxonList();
 
     const filename = path.join("data", options.filename || DEFAULT_FILENAME);
-    const writableStream = fs.createWriteStream( filename );
-    const columns = [
-        "name",
-        "id",
-        "ext",
-        "licenseCode",
-        "attrName",
-    ];
-    const stringifier = stringify( { header: true, columns: columns } );
+    const writableStream = fs.createWriteStream(filename);
+    const columns = ["name", "id", "ext", "licenseCode", "attrName"];
+    const stringifier = stringify({ header: true, columns: columns });
     stringifier.pipe(writableStream);
     const prog = new cliProgress.SingleBar({
         format: "Downloading [{bar}] {percentage}% | ETA: {eta}s | {value}/{total}",
-        etaBuffer: targetTaxa.length
+        etaBuffer: targetTaxa.length,
     });
-    prog.setMaxListeners( 100 );
-    prog.start( targetTaxa.length, 0 );
+    prog.setMaxListeners(100);
+    prog.start(targetTaxa.length, 0);
 
     // Fetch endpoint can load multiple taxa, but it will created some long URLs so best to keep this smallish
-    for ( const batch of chunk( targetTaxa, 30 ) ) {
-        const inatTaxa = await fetchInatTaxa( batch );
-        for ( const taxon of batch ) {
-            prog.increment( );
-            const iNatTaxon = inatTaxa.find( it => it.id === Number( taxon.getINatID() ) );
-            if ( !iNatTaxon ) continue;
-            // Just get the CC-licensed ones, 5 per taxon should be fine (max is 20 on iNat). Whether or not 
+    for (const batch of chunk(targetTaxa, 30)) {
+        const inatTaxa = await fetchInatTaxa(batch);
+        for (const taxon of batch) {
+            prog.increment();
+            const iNatTaxon = inatTaxa.find(
+                (it) => it.id === Number(taxon.getINatID()),
+            );
+            if (!iNatTaxon) continue;
+            // Just get the CC-licensed ones, 5 per taxon should be fine (max is 20 on iNat). Whether or not
             const taxonPhotos = iNatTaxon.taxon_photos
-                .filter( tp => ALLOWED_LICENSE_CODES.includes( tp.photo.license_code ) )
-                .slice( 0, 5 );
+                .filter((tp) =>
+                    ALLOWED_LICENSE_CODES.includes(tp.photo.license_code),
+                )
+                .slice(0, 5);
 
-            for ( const taxonPhoto of taxonPhotos ) {
+            for (const taxonPhoto of taxonPhotos) {
                 const row = [
                     taxon.getName(),
                     taxonPhoto.photo.id,
-                    String( taxonPhoto.photo.medium_url ).split( "." ).at( -1 ),
+                    String(taxonPhoto.photo.medium_url).split(".").at(-1),
                     // Need the license code to do attribution properly
                     taxonPhoto.photo.license_code,
                     // Photographers retain copyright for most CC licenses,
                     // except CC0, so attribution is a bit different
-                    (
-                        taxonPhoto.photo.attribution.match( /\(c\) (.*?),/ )?.[1]
-                        || taxonPhoto.photo.attribution.match( /uploaded by (.*)/ )?.[1]
-                    )
+                    taxonPhoto.photo.attribution.match(/\(c\) (.*?),/)?.[1] ||
+                        taxonPhoto.photo.attribution.match(
+                            /uploaded by (.*)/,
+                        )?.[1],
                 ];
-                stringifier.write( row );
+                stringifier.write(row);
             }
         }
         // iNat will throttle you if you make more than 1 request a second.
         // See https://www.inaturalist.org/pages/api+recommended+practices
-        await sleep( 1_100 );
+        await sleep(1_100);
     }
     prog.stop();
 }
 
 const program = Program.getProgram();
-program.action(getTaxonPhotos).description( "Write a CSV to datadir with iNaturalist taxon photos" )
+program
+    .action(getTaxonPhotos)
+    .description("Write a CSV to datadir with iNaturalist taxon photos")
     .option(
         "-fn, --filename <filename>",
-        "Name of file to write to the data dir"
+        "Name of file to write to the data dir",
     );
 
 await program.parseAsync();

package/lib/inat_photo.js

@@ -1,43 +0,0 @@
-import { CC0, CC_BY, CC_BY_NC, COPYRIGHT, Photo } from "./photo.js";
-
-class InatPhoto extends Photo {
-    /** @type {number} */
-    inatPhotoId;
-    /** @type {string} */
-    ext;
-
-    /**
-     * @param {number} id
-     * @param {string} ext
-     * @param {InatLicenseCode} licenseCode
-     * @param {string} attrName
-     */
-    constructor(id, ext, licenseCode, attrName) {
-        /** @type {typeof COPYRIGHT | typeof CC_BY | typeof CC_BY_NC | typeof CC0} */
-        let rights = COPYRIGHT;
-        if (licenseCode === "cc0") rights = CC0;
-        else if (licenseCode === "cc-by") rights = CC_BY;
-        else if (licenseCode === "cc-by-nc") rights = CC_BY_NC;
-        super(null, attrName, rights);
-        this.inatPhotoId = id;
-        this.ext = ext;
-    }
-
-    getExt() {
-        return this.ext;
-    }
-
-    getId() {
-        return this.inatPhotoId;
-    }
-
-    getUrl() {
-        return `https://inaturalist-open-data.s3.amazonaws.com/photos/${this.inatPhotoId}/medium.${this.ext}`;
-    }
-
-    getSourceUrl() {
-        return `https://www.inaturalist.org/photos/${this.inatPhotoId}`;
-    }
-}
-
-export { InatPhoto };