searchsocket 0.3.1 → 0.3.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (6) hide show
  1. package/dist/cli.js +4 -3
  2. package/dist/index.cjs +3 -2
  3. package/dist/index.js +3 -2
  4. package/dist/sveltekit.cjs +3 -2
  5. package/dist/sveltekit.js +3 -2
  6. package/package.json +1 -1
package/dist/cli.js CHANGED
@@ -12,7 +12,7 @@ import { Command } from "commander";
12
12
  // package.json
13
13
  var package_default = {
14
14
  name: "searchsocket",
15
- version: "0.3.1",
15
+ version: "0.3.2",
16
16
  description: "Semantic site search and MCP retrieval for SvelteKit static sites",
17
17
  license: "MIT",
18
18
  author: "Greg Priday <greg@siteorigin.com>",
@@ -189,7 +189,7 @@ var searchSocketConfigSchema = z.object({
189
189
  ranking: z.object({
190
190
  enableIncomingLinkBoost: z.boolean().optional(),
191
191
  enableDepthBoost: z.boolean().optional(),
192
- pageWeights: z.record(z.string(), z.number().positive()).optional(),
192
+ pageWeights: z.record(z.string(), z.number().min(0)).optional(),
193
193
  aggregationCap: z.number().int().positive().optional(),
194
194
  aggregationDecay: z.number().min(0).max(1).optional(),
195
195
  minChunkScoreRatio: z.number().min(0).max(1).optional(),
@@ -1700,7 +1700,7 @@ function extractFromHtml(url, html, config) {
1700
1700
  const $ = load(html);
1701
1701
  const normalizedUrl = normalizeUrlPath(url);
1702
1702
  const pageBaseUrl = new URL(`https://searchsocket.local${normalizedUrl}`);
1703
- const title = normalizeText($("title").first().text() || "") || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || normalizedUrl;
1703
+ const title = $("meta[property='og:title']").attr("content")?.trim() || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || $("meta[name='twitter:title']").attr("content")?.trim() || normalizeText($("title").first().text() || "") || normalizedUrl;
1704
1704
  if (config.extract.respectRobotsNoindex) {
1705
1705
  const robots = $("meta[name='robots']").attr("content") ?? "";
1706
1706
  if (/\bnoindex\b/i.test(robots)) {
@@ -3010,6 +3010,7 @@ function aggregateByPage(ranked, config) {
3010
3010
  }
3011
3011
  let pageScore = maxScore + aggregationBonus * config.ranking.weights.aggregation;
3012
3012
  const pageWeight = findPageWeight(url, config.ranking.pageWeights);
3013
+ if (pageWeight === 0) continue;
3013
3014
  if (pageWeight !== 1) {
3014
3015
  pageScore *= pageWeight;
3015
3016
  }
package/dist/index.cjs CHANGED
@@ -16688,7 +16688,7 @@ var searchSocketConfigSchema = zod.z.object({
16688
16688
  ranking: zod.z.object({
16689
16689
  enableIncomingLinkBoost: zod.z.boolean().optional(),
16690
16690
  enableDepthBoost: zod.z.boolean().optional(),
16691
- pageWeights: zod.z.record(zod.z.string(), zod.z.number().positive()).optional(),
16691
+ pageWeights: zod.z.record(zod.z.string(), zod.z.number().min(0)).optional(),
16692
16692
  aggregationCap: zod.z.number().int().positive().optional(),
16693
16693
  aggregationDecay: zod.z.number().min(0).max(1).optional(),
16694
16694
  minChunkScoreRatio: zod.z.number().min(0).max(1).optional(),
@@ -19038,7 +19038,7 @@ function extractFromHtml(url, html, config) {
19038
19038
  const $ = cheerio.load(html);
19039
19039
  const normalizedUrl = normalizeUrlPath(url);
19040
19040
  const pageBaseUrl = new URL(`https://searchsocket.local${normalizedUrl}`);
19041
- const title = normalizeText($("title").first().text() || "") || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || normalizedUrl;
19041
+ const title = $("meta[property='og:title']").attr("content")?.trim() || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || $("meta[name='twitter:title']").attr("content")?.trim() || normalizeText($("title").first().text() || "") || normalizedUrl;
19042
19042
  if (config.extract.respectRobotsNoindex) {
19043
19043
  const robots = $("meta[name='robots']").attr("content") ?? "";
19044
19044
  if (/\bnoindex\b/i.test(robots)) {
@@ -20279,6 +20279,7 @@ function aggregateByPage(ranked, config) {
20279
20279
  }
20280
20280
  let pageScore = maxScore + aggregationBonus * config.ranking.weights.aggregation;
20281
20281
  const pageWeight = findPageWeight(url, config.ranking.pageWeights);
20282
+ if (pageWeight === 0) continue;
20282
20283
  if (pageWeight !== 1) {
20283
20284
  pageScore *= pageWeight;
20284
20285
  }
package/dist/index.js CHANGED
@@ -16676,7 +16676,7 @@ var searchSocketConfigSchema = z.object({
16676
16676
  ranking: z.object({
16677
16677
  enableIncomingLinkBoost: z.boolean().optional(),
16678
16678
  enableDepthBoost: z.boolean().optional(),
16679
- pageWeights: z.record(z.string(), z.number().positive()).optional(),
16679
+ pageWeights: z.record(z.string(), z.number().min(0)).optional(),
16680
16680
  aggregationCap: z.number().int().positive().optional(),
16681
16681
  aggregationDecay: z.number().min(0).max(1).optional(),
16682
16682
  minChunkScoreRatio: z.number().min(0).max(1).optional(),
@@ -19026,7 +19026,7 @@ function extractFromHtml(url, html, config) {
19026
19026
  const $ = load(html);
19027
19027
  const normalizedUrl = normalizeUrlPath(url);
19028
19028
  const pageBaseUrl = new URL(`https://searchsocket.local${normalizedUrl}`);
19029
- const title = normalizeText($("title").first().text() || "") || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || normalizedUrl;
19029
+ const title = $("meta[property='og:title']").attr("content")?.trim() || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || $("meta[name='twitter:title']").attr("content")?.trim() || normalizeText($("title").first().text() || "") || normalizedUrl;
19030
19030
  if (config.extract.respectRobotsNoindex) {
19031
19031
  const robots = $("meta[name='robots']").attr("content") ?? "";
19032
19032
  if (/\bnoindex\b/i.test(robots)) {
@@ -20267,6 +20267,7 @@ function aggregateByPage(ranked, config) {
20267
20267
  }
20268
20268
  let pageScore = maxScore + aggregationBonus * config.ranking.weights.aggregation;
20269
20269
  const pageWeight = findPageWeight(url, config.ranking.pageWeights);
20270
+ if (pageWeight === 0) continue;
20270
20271
  if (pageWeight !== 1) {
20271
20272
  pageScore *= pageWeight;
20272
20273
  }
package/dist/sveltekit.cjs CHANGED
@@ -16684,7 +16684,7 @@ var searchSocketConfigSchema = zod.z.object({
16684
16684
  ranking: zod.z.object({
16685
16685
  enableIncomingLinkBoost: zod.z.boolean().optional(),
16686
16686
  enableDepthBoost: zod.z.boolean().optional(),
16687
- pageWeights: zod.z.record(zod.z.string(), zod.z.number().positive()).optional(),
16687
+ pageWeights: zod.z.record(zod.z.string(), zod.z.number().min(0)).optional(),
16688
16688
  aggregationCap: zod.z.number().int().positive().optional(),
16689
16689
  aggregationDecay: zod.z.number().min(0).max(1).optional(),
16690
16690
  minChunkScoreRatio: zod.z.number().min(0).max(1).optional(),
@@ -17940,6 +17940,7 @@ function aggregateByPage(ranked, config) {
17940
17940
  }
17941
17941
  let pageScore = maxScore + aggregationBonus * config.ranking.weights.aggregation;
17942
17942
  const pageWeight = findPageWeight(url, config.ranking.pageWeights);
17943
+ if (pageWeight === 0) continue;
17943
17944
  if (pageWeight !== 1) {
17944
17945
  pageScore *= pageWeight;
17945
17946
  }
@@ -19580,7 +19581,7 @@ function extractFromHtml(url, html, config) {
19580
19581
  const $ = cheerio.load(html);
19581
19582
  const normalizedUrl = normalizeUrlPath(url);
19582
19583
  const pageBaseUrl = new URL(`https://searchsocket.local${normalizedUrl}`);
19583
- const title = normalizeText($("title").first().text() || "") || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || normalizedUrl;
19584
+ const title = $("meta[property='og:title']").attr("content")?.trim() || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || $("meta[name='twitter:title']").attr("content")?.trim() || normalizeText($("title").first().text() || "") || normalizedUrl;
19584
19585
  if (config.extract.respectRobotsNoindex) {
19585
19586
  const robots = $("meta[name='robots']").attr("content") ?? "";
19586
19587
  if (/\bnoindex\b/i.test(robots)) {
package/dist/sveltekit.js CHANGED
@@ -16672,7 +16672,7 @@ var searchSocketConfigSchema = z.object({
16672
16672
  ranking: z.object({
16673
16673
  enableIncomingLinkBoost: z.boolean().optional(),
16674
16674
  enableDepthBoost: z.boolean().optional(),
16675
- pageWeights: z.record(z.string(), z.number().positive()).optional(),
16675
+ pageWeights: z.record(z.string(), z.number().min(0)).optional(),
16676
16676
  aggregationCap: z.number().int().positive().optional(),
16677
16677
  aggregationDecay: z.number().min(0).max(1).optional(),
16678
16678
  minChunkScoreRatio: z.number().min(0).max(1).optional(),
@@ -17928,6 +17928,7 @@ function aggregateByPage(ranked, config) {
17928
17928
  }
17929
17929
  let pageScore = maxScore + aggregationBonus * config.ranking.weights.aggregation;
17930
17930
  const pageWeight = findPageWeight(url, config.ranking.pageWeights);
17931
+ if (pageWeight === 0) continue;
17931
17932
  if (pageWeight !== 1) {
17932
17933
  pageScore *= pageWeight;
17933
17934
  }
@@ -19568,7 +19569,7 @@ function extractFromHtml(url, html, config) {
19568
19569
  const $ = load(html);
19569
19570
  const normalizedUrl = normalizeUrlPath(url);
19570
19571
  const pageBaseUrl = new URL(`https://searchsocket.local${normalizedUrl}`);
19571
- const title = normalizeText($("title").first().text() || "") || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || normalizedUrl;
19572
+ const title = $("meta[property='og:title']").attr("content")?.trim() || normalizeText($(`${config.extract.mainSelector} h1`).first().text() || "") || $("meta[name='twitter:title']").attr("content")?.trim() || normalizeText($("title").first().text() || "") || normalizedUrl;
19572
19573
  if (config.extract.respectRobotsNoindex) {
19573
19574
  const robots = $("meta[name='robots']").attr("content") ?? "";
19574
19575
  if (/\bnoindex\b/i.test(robots)) {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "searchsocket",
3
- "version": "0.3.1",
3
+ "version": "0.3.2",
4
4
  "description": "Semantic site search and MCP retrieval for SvelteKit static sites",
5
5
  "license": "MIT",
6
6
  "author": "Greg Priday <greg@siteorigin.com>",