doc2vec 2.11.0 → 2.13.0

package/dist/ui/index.html

@@ -5,8 +5,8 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>doc2vec</title>
     <link rel="icon" href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'%3E%3Ctext y='0.9em' font-size='90'%3E%F0%9F%93%9A%3C/text%3E%3C/svg%3E" />
-    <script type="module" crossorigin src="/assets/index-D-QOw3rk.js"></script>
-    <link rel="stylesheet" crossorigin href="/assets/index-BVg6n7Si.css">
+    <script type="module" crossorigin src="/assets/index-zutKK2b4.js"></script>
+    <link rel="stylesheet" crossorigin href="/assets/index-C-uNubcD.css">
   </head>
   <body>
     <div id="root"></div>

package/dist/utils.js

@@ -119,5 +119,63 @@ class Utils {
     static tokenize(text) {
         return text.split(/(\s+)/).filter(token => token.length > 0);
     }
+    /**
+     * Extract the `rel="next"` URL from an RFC 5988 Link header.
+     *
+     * GitHub's list endpoints cap page-number pagination (`?page=N`) and reject
+     * deeper offsets with HTTP 422 ("please use cursor based pagination"), so
+     * walking a large result set requires following these URLs — they already
+     * carry the opaque `after=` cursor and must be passed through verbatim
+     * rather than rebuilt from parts.
+     */
+    static parseNextLink(linkHeader) {
+        if (!linkHeader)
+            return null;
+        for (const part of linkHeader.split(',')) {
+            const match = part.match(/<([^>]+)>\s*;\s*rel\s*=\s*"?next"?/i);
+            if (match)
+                return match[1].trim();
+        }
+        return null;
+    }
+    /**
+     * Drop unpaired UTF-16 surrogates.
+     *
+     * A lone surrogate is not valid UTF-8, so strict JSON parsers reject the
+     * whole request body — Qdrant answers 400 "lone leading surrogate in hex
+     * escape" and the chunk is lost. Content can arrive this way from an
+     * upstream source, so sanitize before storing.
+     */
+    static stripLoneSurrogates(text) {
+        // Node 20+ exposes toWellFormed(), which replaces lone surrogates with
+        // U+FFFD. Removing them outright keeps the text closer to the original.
+        return text
+            .replace(/[\uD800-\uDBFF](?![\uDC00-\uDFFF])/g, '')
+            .replace(/(^|[^\uD800-\uDBFF])([\uDC00-\uDFFF])/g, '$1');
+    }
+    /**
+     * Slice a string without splitting a surrogate pair.
+     *
+     * Plain `slice()` works on UTF-16 code units, so a boundary landing inside
+     * a pair (emoji, some CJK) leaves a lone surrogate on each side. Both
+     * boundaries are nudged the same way — a straddled pair always travels with
+     * the *following* slice — so consecutive slices stay lossless: no pair falls
+     * into the gap between them, and none is duplicated.
+     */
+    static sliceSafe(text, start, end) {
+        const isHigh = (code) => code >= 0xd800 && code <= 0xdbff;
+        const isLow = (code) => code >= 0xdc00 && code <= 0xdfff;
+        // True when the pair straddling `index` must move to the next slice
+        const straddles = (index) => index > 0 && index < text.length && isHigh(text.charCodeAt(index - 1)) && isLow(text.charCodeAt(index));
+        let from = Math.max(0, Math.min(start, text.length));
+        let to = Math.max(from, Math.min(text.length, end));
+        // Step back to pick up the high half the previous slice left behind
+        if (straddles(from))
+            from--;
+        // Leave the whole pair for the next slice
+        if (to > from && straddles(to))
+            to--;
+        return text.slice(from, to);
+    }
 }
 exports.Utils = Utils;

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "doc2vec",
-    "version": "2.11.0",
+    "version": "2.13.0",
     "type": "commonjs",
     "description": "",
     "main": "dist/doc2vec.js",

package/dist/ui/assets/index-BVg6n7Si.css

@@ -1 +0,0 @@
-@layer properties{@supports (((-webkit-hyphens:none)) and (not (margin-trim:inline))) or ((-moz-orient:inline) and (not (color:rgb(from red r g b)))){*,:before,:after,::backdrop{--tw-space-y-reverse:0;--tw-border-style:solid;--tw-leading:initial;--tw-font-weight:initial;--tw-tracking:initial;--tw-shadow:0 0 #0000;--tw-shadow-color:initial;--tw-shadow-alpha:100%;--tw-inset-shadow:0 0 #0000;--tw-inset-shadow-color:initial;--tw-inset-shadow-alpha:100%;--tw-ring-color:initial;--tw-ring-shadow:0 0 #0000;--tw-inset-ring-color:initial;--tw-inset-ring-shadow:0 0 #0000;--tw-ring-inset:initial;--tw-ring-offset-width:0px;--tw-ring-offset-color:#fff;--tw-ring-offset-shadow:0 0 #0000}}}@layer theme{:root,:host{--font-mono:ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;--color-white:#fff;--spacing:.25rem;--container-md:28rem;--container-6xl:72rem;--text-xs:.75rem;--text-xs--line-height:calc(1 / .75);--text-sm:.875rem;--text-sm--line-height:calc(1.25 / .875);--text-lg:1.125rem;--text-lg--line-height:calc(1.75 / 1.125);--text-xl:1.25rem;--text-xl--line-height:calc(1.75 / 1.25);--text-2xl:1.5rem;--text-2xl--line-height:calc(2 / 1.5);--font-weight-normal:400;--font-weight-medium:500;--font-weight-semibold:600;--tracking-tight:-.025em;--tracking-wide:.025em;--radius-md:.375rem;--radius-lg:.5rem;--animate-pulse:pulse 2s cubic-bezier(.4, 0, .6, 1) infinite;--default-transition-duration:.15s;--default-transition-timing-function:cubic-bezier(.4, 0, .2, 1);--default-font-family:system-ui, -apple-system, "Segoe UI", sans-serif;--default-mono-font-family:var(--font-mono)}}@layer base{*,:after,:before,::backdrop{box-sizing:border-box;border:0 solid;margin:0;padding:0}::file-selector-button{box-sizing:border-box;border:0 solid;margin:0;padding:0}html,:host{-webkit-text-size-adjust:100%;tab-size:4;line-height:1.5;font-family:var(--default-font-family,ui-sans-serif, system-ui, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji");font-feature-settings:var(--default-font-feature-settings,normal);font-variation-settings:var(--default-font-variation-settings,normal);-webkit-tap-highlight-color:transparent}hr{height:0;color:inherit;border-top-width:1px}abbr:where([title]){-webkit-text-decoration:underline dotted;text-decoration:underline dotted}h1,h2,h3,h4,h5,h6{font-size:inherit;font-weight:inherit}a{color:inherit;-webkit-text-decoration:inherit;text-decoration:inherit}b,strong{font-weight:bolder}code,kbd,samp,pre{font-family:var(--default-mono-font-family,ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace);font-feature-settings:var(--default-mono-font-feature-settings,normal);font-variation-settings:var(--default-mono-font-variation-settings,normal);font-size:1em}small{font-size:80%}sub,sup{vertical-align:baseline;font-size:75%;line-height:0;position:relative}sub{bottom:-.25em}sup{top:-.5em}table{text-indent:0;border-color:inherit;border-collapse:collapse}:-moz-focusring{outline:auto}progress{vertical-align:baseline}summary{display:list-item}ol,ul,menu{list-style:none}img,svg,video,canvas,audio,iframe,embed,object{vertical-align:middle;display:block}img,video{max-width:100%;height:auto}button,input,select,optgroup,textarea{font:inherit;font-feature-settings:inherit;font-variation-settings:inherit;letter-spacing:inherit;color:inherit;opacity:1;background-color:#0000;border-radius:0}::file-selector-button{font:inherit;font-feature-settings:inherit;font-variation-settings:inherit;letter-spacing:inherit;color:inherit;opacity:1;background-color:#0000;border-radius:0}:where(select:is([multiple],[size])) optgroup{font-weight:bolder}:where(select:is([multiple],[size])) optgroup option{padding-inline-start:20px}::file-selector-button{margin-inline-end:4px}::placeholder{opacity:1}@supports (not ((-webkit-appearance:-apple-pay-button))) or (contain-intrinsic-size:1px){::placeholder{color:currentColor}@supports (color:color-mix(in lab,red,red)){::placeholder{color:color-mix(in oklab,currentcolor 50%,transparent)}}}textarea{resize:vertical}::-webkit-search-decoration{-webkit-appearance:none}::-webkit-date-and-time-value{min-height:1lh;text-align:inherit}::-webkit-datetime-edit{display:inline-flex}::-webkit-datetime-edit-fields-wrapper{padding:0}::-webkit-datetime-edit{padding-block:0}::-webkit-datetime-edit-year-field{padding-block:0}::-webkit-datetime-edit-month-field{padding-block:0}::-webkit-datetime-edit-day-field{padding-block:0}::-webkit-datetime-edit-hour-field{padding-block:0}::-webkit-datetime-edit-minute-field{padding-block:0}::-webkit-datetime-edit-second-field{padding-block:0}::-webkit-datetime-edit-millisecond-field{padding-block:0}::-webkit-datetime-edit-meridiem-field{padding-block:0}::-webkit-calendar-picker-indicator{line-height:1}:-moz-ui-invalid{box-shadow:none}button,input:where([type=button],[type=reset],[type=submit]){appearance:button}::file-selector-button{appearance:button}::-webkit-inner-spin-button{height:auto}::-webkit-outer-spin-button{height:auto}[hidden]:where(:not([hidden=until-found])){display:none!important}}@layer components;@layer utilities{.mx-auto{margin-inline:auto}.mt-0\.5{margin-top:calc(var(--spacing) * .5)}.mt-1{margin-top:var(--spacing)}.mt-1\.5{margin-top:calc(var(--spacing) * 1.5)}.mt-2{margin-top:calc(var(--spacing) * 2)}.mt-3{margin-top:calc(var(--spacing) * 3)}.-mb-px{margin-bottom:-1px}.mb-1{margin-bottom:var(--spacing)}.mb-2{margin-bottom:calc(var(--spacing) * 2)}.mb-3{margin-bottom:calc(var(--spacing) * 3)}.mb-4{margin-bottom:calc(var(--spacing) * 4)}.ml-1{margin-left:var(--spacing)}.ml-2{margin-left:calc(var(--spacing) * 2)}.ml-auto{margin-left:auto}.block{display:block}.flex{display:flex}.grid{display:grid}.hidden{display:none}.inline-block{display:inline-block}.inline-flex{display:inline-flex}.h-2{height:calc(var(--spacing) * 2)}.h-4{height:calc(var(--spacing) * 4)}.max-h-\[560px\]{max-height:560px}.min-h-screen{min-height:100vh}.w-2{width:calc(var(--spacing) * 2)}.w-4{width:calc(var(--spacing) * 4)}.w-10{width:calc(var(--spacing) * 10)}.w-44{width:calc(var(--spacing) * 44)}.w-72{width:calc(var(--spacing) * 72)}.w-full{width:100%}.max-w-6xl{max-width:var(--container-6xl)}.max-w-md{max-width:var(--container-md)}.min-w-48{min-width:calc(var(--spacing) * 48)}.flex-1{flex:1}.shrink-0{flex-shrink:0}.animate-pulse{animation:var(--animate-pulse)}.grid-cols-2{grid-template-columns:repeat(2,minmax(0,1fr))}.flex-wrap{flex-wrap:wrap}.items-baseline{align-items:baseline}.items-center{align-items:center}.items-start{align-items:flex-start}.justify-between{justify-content:space-between}.gap-1{gap:var(--spacing)}.gap-1\.5{gap:calc(var(--spacing) * 1.5)}.gap-2{gap:calc(var(--spacing) * 2)}.gap-3{gap:calc(var(--spacing) * 3)}.gap-4{gap:calc(var(--spacing) * 4)}.gap-6{gap:calc(var(--spacing) * 6)}:where(.space-y-3>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(calc(var(--spacing) * 3) * var(--tw-space-y-reverse));margin-block-end:calc(calc(var(--spacing) * 3) * calc(1 - var(--tw-space-y-reverse)))}:where(.space-y-4>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(calc(var(--spacing) * 4) * var(--tw-space-y-reverse));margin-block-end:calc(calc(var(--spacing) * 4) * calc(1 - var(--tw-space-y-reverse)))}:where(.space-y-6>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(calc(var(--spacing) * 6) * var(--tw-space-y-reverse));margin-block-end:calc(calc(var(--spacing) * 6) * calc(1 - var(--tw-space-y-reverse)))}.gap-x-4{column-gap:calc(var(--spacing) * 4)}.gap-x-6{column-gap:calc(var(--spacing) * 6)}.gap-x-8{column-gap:calc(var(--spacing) * 8)}.gap-y-2{row-gap:calc(var(--spacing) * 2)}.gap-y-3{row-gap:calc(var(--spacing) * 3)}.self-center{align-self:center}.truncate{text-overflow:ellipsis;white-space:nowrap;overflow:hidden}.overflow-auto{overflow:auto}.overflow-hidden{overflow:hidden}.overflow-x-auto{overflow-x:auto}.rounded{border-radius:.25rem}.rounded-full{border-radius:3.40282e38px}.rounded-lg{border-radius:var(--radius-lg)}.rounded-md{border-radius:var(--radius-md)}.border{border-style:var(--tw-border-style);border-width:1px}.border-b{border-bottom-style:var(--tw-border-style);border-bottom-width:1px}.border-b-2{border-bottom-style:var(--tw-border-style);border-bottom-width:2px}.border-dashed{--tw-border-style:dashed;border-style:dashed}.border-accent,.border-accent\/30{border-color:var(--accent)}@supports (color:color-mix(in lab,red,red)){.border-accent\/30{border-color:color-mix(in oklab,var(--accent) 30%,transparent)}}.border-accent\/40{border-color:var(--accent)}@supports (color:color-mix(in lab,red,red)){.border-accent\/40{border-color:color-mix(in oklab,var(--accent) 40%,transparent)}}.border-critical\/40{border-color:var(--status-critical)}@supports (color:color-mix(in lab,red,red)){.border-critical\/40{border-color:color-mix(in oklab,var(--status-critical) 40%,transparent)}}.border-critical\/50{border-color:var(--status-critical)}@supports (color:color-mix(in lab,red,red)){.border-critical\/50{border-color:color-mix(in oklab,var(--status-critical) 50%,transparent)}}.border-current{border-color:currentColor}.border-edge,.border-edge\/60{border-color:var(--border)}@supports (color:color-mix(in lab,red,red)){.border-edge\/60{border-color:color-mix(in oklab,var(--border) 60%,transparent)}}.border-good\/40{border-color:var(--status-good)}@supports (color:color-mix(in lab,red,red)){.border-good\/40{border-color:color-mix(in oklab,var(--status-good) 40%,transparent)}}.border-transparent{border-color:#0000}.border-warning\/40{border-color:var(--status-warning)}@supports (color:color-mix(in lab,red,red)){.border-warning\/40{border-color:color-mix(in oklab,var(--status-warning) 40%,transparent)}}.border-warning\/50{border-color:var(--status-warning)}@supports (color:color-mix(in lab,red,red)){.border-warning\/50{border-color:color-mix(in oklab,var(--status-warning) 50%,transparent)}}.bg-accent{background-color:var(--accent)}.bg-page{background-color:var(--page)}.bg-surface{background-color:var(--surface-1)}.p-4{padding:calc(var(--spacing) * 4)}.px-1{padding-inline:var(--spacing)}.px-2{padding-inline:calc(var(--spacing) * 2)}.px-2\.5{padding-inline:calc(var(--spacing) * 2.5)}.px-3{padding-inline:calc(var(--spacing) * 3)}.px-3\.5{padding-inline:calc(var(--spacing) * 3.5)}.px-4{padding-inline:calc(var(--spacing) * 4)}.px-6{padding-inline:calc(var(--spacing) * 6)}.py-0\.5{padding-block:calc(var(--spacing) * .5)}.py-1{padding-block:var(--spacing)}.py-1\.5{padding-block:calc(var(--spacing) * 1.5)}.py-2{padding-block:calc(var(--spacing) * 2)}.py-2\.5{padding-block:calc(var(--spacing) * 2.5)}.py-3{padding-block:calc(var(--spacing) * 3)}.py-4{padding-block:calc(var(--spacing) * 4)}.py-8{padding-block:calc(var(--spacing) * 8)}.py-10{padding-block:calc(var(--spacing) * 10)}.pr-4{padding-right:calc(var(--spacing) * 4)}.pb-2{padding-bottom:calc(var(--spacing) * 2)}.text-center{text-align:center}.text-left{text-align:left}.font-mono{font-family:var(--font-mono)}.text-2xl{font-size:var(--text-2xl);line-height:var(--tw-leading,var(--text-2xl--line-height))}.text-lg{font-size:var(--text-lg);line-height:var(--tw-leading,var(--text-lg--line-height))}.text-sm{font-size:var(--text-sm);line-height:var(--tw-leading,var(--text-sm--line-height))}.text-xl{font-size:var(--text-xl);line-height:var(--tw-leading,var(--text-xl--line-height))}.text-xs{font-size:var(--text-xs);line-height:var(--tw-leading,var(--text-xs--line-height))}.text-\[10px\]{font-size:10px}.leading-5{--tw-leading:calc(var(--spacing) * 5);line-height:calc(var(--spacing) * 5)}.font-medium{--tw-font-weight:var(--font-weight-medium);font-weight:var(--font-weight-medium)}.font-normal{--tw-font-weight:var(--font-weight-normal);font-weight:var(--font-weight-normal)}.font-semibold{--tw-font-weight:var(--font-weight-semibold);font-weight:var(--font-weight-semibold)}.tracking-tight{--tw-tracking:var(--tracking-tight);letter-spacing:var(--tracking-tight)}.tracking-wide{--tw-tracking:var(--tracking-wide);letter-spacing:var(--tracking-wide)}.break-all{word-break:break-all}.whitespace-pre-wrap{white-space:pre-wrap}.text-accent{color:var(--accent)}.text-critical{color:var(--status-critical)}.text-good-text{color:var(--good-text)}.text-ink{color:var(--text-primary)}.text-ink-muted{color:var(--text-muted)}.text-ink-secondary{color:var(--text-secondary)}.text-warning{color:var(--status-warning)}.text-white{color:var(--color-white)}.capitalize{text-transform:capitalize}.uppercase{text-transform:uppercase}.underline-offset-2{text-underline-offset:2px}.accent-\(--accent\){accent-color:var(--accent)}.shadow-sm{--tw-shadow:0 1px 3px 0 var(--tw-shadow-color,#0000001a), 0 1px 2px -1px var(--tw-shadow-color,#0000001a);box-shadow:var(--tw-inset-shadow),var(--tw-inset-ring-shadow),var(--tw-ring-offset-shadow),var(--tw-ring-shadow),var(--tw-shadow)}.transition{transition-property:color,background-color,border-color,outline-color,text-decoration-color,fill,stroke,--tw-gradient-from,--tw-gradient-via,--tw-gradient-to,opacity,box-shadow,transform,translate,scale,rotate,filter,-webkit-backdrop-filter,backdrop-filter,display,content-visibility,overlay,pointer-events;transition-timing-function:var(--tw-ease,var(--default-transition-timing-function));transition-duration:var(--tw-duration,var(--default-transition-duration))}.outline-none{--tw-outline-style:none;outline-style:none}.select-none{-webkit-user-select:none;user-select:none}.placeholder\:text-ink-muted\/60::placeholder{color:var(--text-muted)}@supports (color:color-mix(in lab,red,red)){.placeholder\:text-ink-muted\/60::placeholder{color:color-mix(in oklab,var(--text-muted) 60%,transparent)}}.last\:border-0:last-child{border-style:var(--tw-border-style);border-width:0}@media(hover:hover){.hover\:border-accent:hover,.hover\:border-accent\/50:hover{border-color:var(--accent)}@supports (color:color-mix(in lab,red,red)){.hover\:border-accent\/50:hover{border-color:color-mix(in oklab,var(--accent) 50%,transparent)}}.hover\:bg-critical\/10:hover{background-color:var(--status-critical)}@supports (color:color-mix(in lab,red,red)){.hover\:bg-critical\/10:hover{background-color:color-mix(in oklab,var(--status-critical) 10%,transparent)}}.hover\:bg-ink\/\[0\.03\]:hover{background-color:var(--text-primary)}@supports (color:color-mix(in lab,red,red)){.hover\:bg-ink\/\[0\.03\]:hover{background-color:color-mix(in oklab,var(--text-primary) 3%,transparent)}}.hover\:text-accent:hover{color:var(--accent)}.hover\:text-critical:hover{color:var(--status-critical)}.hover\:text-ink-secondary:hover{color:var(--text-secondary)}.hover\:underline:hover{text-decoration-line:underline}.hover\:opacity-90:hover{opacity:.9}}.focus\:border-accent:focus{border-color:var(--accent)}.disabled\:cursor-not-allowed:disabled{cursor:not-allowed}.disabled\:opacity-40:disabled{opacity:.4}@media(min-width:40rem){.sm\:col-span-2{grid-column:span 2/span 2}.sm\:grid-cols-2{grid-template-columns:repeat(2,minmax(0,1fr))}}@media(min-width:48rem){.md\:grid-cols-4{grid-template-columns:repeat(4,minmax(0,1fr))}}}:root{--page:#f9f9f7;--surface-1:#fcfcfb;--text-primary:#0b0b0b;--text-secondary:#52514e;--text-muted:#898781;--gridline:#e1e0d9;--baseline:#c3c2b7;--border:#0b0b0b1a;--series-1:#2a78d6;--status-good:#0ca30c;--status-warning:#fab219;--status-critical:#d03b3b;--good-text:#006300;--accent:#2a78d6}@media(prefers-color-scheme:dark){:root{--page:#0d0d0d;--surface-1:#1a1a19;--text-primary:#fff;--text-secondary:#c3c2b7;--text-muted:#898781;--gridline:#2c2c2a;--baseline:#383835;--border:#ffffff1a;--series-1:#3987e5;--status-good:#0ca30c;--status-warning:#fab219;--status-critical:#d03b3b;--good-text:#0ca30c;--accent:#3987e5}}html{background:var(--page);color:var(--text-primary);font-family:system-ui,-apple-system,Segoe UI,sans-serif}.log-scroll::-webkit-scrollbar{width:10px;height:10px}.log-scroll::-webkit-scrollbar-thumb{background:var(--baseline);border-radius:5px}@property --tw-space-y-reverse{syntax:"*";inherits:false;initial-value:0}@property --tw-border-style{syntax:"*";inherits:false;initial-value:solid}@property --tw-leading{syntax:"*";inherits:false}@property --tw-font-weight{syntax:"*";inherits:false}@property --tw-tracking{syntax:"*";inherits:false}@property --tw-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@property --tw-shadow-color{syntax:"*";inherits:false}@property --tw-shadow-alpha{syntax:"<percentage>";inherits:false;initial-value:100%}@property --tw-inset-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@property --tw-inset-shadow-color{syntax:"*";inherits:false}@property --tw-inset-shadow-alpha{syntax:"<percentage>";inherits:false;initial-value:100%}@property --tw-ring-color{syntax:"*";inherits:false}@property --tw-ring-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@property --tw-inset-ring-color{syntax:"*";inherits:false}@property --tw-inset-ring-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@property --tw-ring-inset{syntax:"*";inherits:false}@property --tw-ring-offset-width{syntax:"<length>";inherits:false;initial-value:0}@property --tw-ring-offset-color{syntax:"*";inherits:false;initial-value:#fff}@property --tw-ring-offset-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@keyframes pulse{50%{opacity:.5}}