lingdocs
/
pashto-inflector
mirror of https://github.com/lingdocs/pashto-inflector.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

phonetics conversion done

This commit is contained in:
adueck 2023-07-27 12:28:50 +04:00
parent fc97db0dd3
commit c0cd34c3d6
11 changed files with 4890 additions and 4018 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

734
src/components/src/blocks/Block.tsx
View File

@ -1,46 +1,93 @@
import * as T from "../../../types";
import classNames from "classnames";
import { getEnglishFromRendered } from "../../../lib/src/phrase-building/np-tools";
import {
getEnglishFromRendered,
} from "../../../lib/src/phrase-building/np-tools";
import { getEnglishPersonInfo, getEnglishParticipleInflection, getEnglishGenNumInfo } from "../../../lib/src/misc-helpers";
getEnglishPersonInfo,
getEnglishParticipleInflection,
getEnglishGenNumInfo,
} from "../../../lib/src/misc-helpers";
import { useState } from "react";
import { getLength } from "../../../lib/src/p-text-helpers";
import { roleIcon } from "../vp-explorer/VPExplorerExplanationModal";
import { negativeParticle } from "../../../lib/src/grammar-units";
function Block({ opts, block, king, script }: {
opts: T.TextOptions,
block: T.Block,
king?: "subject" | "object" | undefined,
function Block({
opts,
block,
king,
script,
}: {
opts: T.TextOptions;
block: T.Block;
king?: "subject" | "object" | undefined;
script: "p" | "f";
}) {
if ("equative" in block.block) {
return <EquativeBlock opts={opts} eq={block.block.equative} script={script} />;
return (
<EquativeBlock opts={opts} eq={block.block.equative} script={script} />
);
}
if (block.block.type === "AP") {
const english = getEnglishFromRendered(block.block);
return <APBlock opts={opts} english={english} script={script}>{block.block}</APBlock>
return (
<APBlock opts={opts} english={english} script={script}>
{block.block}
</APBlock>
);
}
if (block.block.type === "subjectSelection") {
const role = king === "subject" ? "king" : king === "object" ? "servant" : undefined;
return <SubjectBlock opts={opts} np={block.block.selection} role={role} script={script} />
const role =
king === "subject" ? "king" : king === "object" ? "servant" : undefined;
return (
<SubjectBlock
opts={opts}
np={block.block.selection}
role={role}
script={script}
/>
);
}
if (block.block.type === "objectSelection") {
const role = king === "object" ? "king" : king === "subject" ? "servant" : undefined;
return <ObjectBlock opts={opts} obj={block.block.selection} role={role} script={script} />;
const role =
king === "object" ? "king" : king === "subject" ? "servant" : undefined;
return (
<ObjectBlock
opts={opts}
obj={block.block.selection}
role={role}
script={script}
/>
);
}
if (block.block.type === "predicateSelection") {
const english = getEnglishFromRendered(block.block.selection);
return <div className="text-center">
<div><strong>Predicate</strong></div>
{block.block.selection.type === "complement"
? <ComplementBlock opts={opts} comp={block.block.selection.selection} script={script} />
: <NPBlock opts={opts} english={english} script={script}>{block.block.selection}</NPBlock>}
return (
<div className="text-center">
<div>
<strong>Predicate</strong>
</div>
{block.block.selection.type === "complement" ? (
<ComplementBlock
opts={opts}
comp={block.block.selection.selection}
script={script}
/>
) : (
<NPBlock opts={opts} english={english} script={script}>
{block.block.selection}
</NPBlock>
)}
</div>
);
}
if (block.block.type === "negative") {
return <NegBlock opts={opts} imperative={block.block.imperative} script={script} />
return (
<NegBlock
opts={opts}
imperative={block.block.imperative}
script={script}
/>
);
}
if (block.block.type === "PH") {
return <PerfHeadBlock opts={opts} ps={block.block.ps} script={script} />;
@ -49,19 +96,36 @@ function Block({ opts, block, king, script }: {
return <VBBlock opts={opts} block={block.block} script={script} />;
}
if (block.block.type === "complement") {
return <ComplementBlock opts={opts} comp={block.block.selection} script={script} />
return (
<ComplementBlock
opts={opts}
comp={block.block.selection}
script={script}
/>
);
}
if (block.block.type === "NComp") {
return <NCompBlock opts={opts} comp={block.block.comp} script={script} />
return <NCompBlock opts={opts} comp={block.block.comp} script={script} />;
}
return <WeldedBlock opts={opts} welded={block.block} script={script} />
return <WeldedBlock opts={opts} welded={block.block} script={script} />;
}
export default Block;
function Border({ children, extraClassName, padding }: { children: JSX.Element | JSX.Element[] | string, extraClassName?: string, padding?: string }) {
return <div
className={`block-border d-flex flex-row justify-content-center align-items-center ${extraClassName ? extraClassName : ""}`}
function Border({
children,
extraClassName,
padding,
}: {
children: JSX.Element | JSX.Element[] | string;
extraClassName?: string;
padding?: string;
}) {
return (
<div
className={`block-border d-flex flex-row justify-content-center align-items-center ${
extraClassName ? extraClassName : ""
}`}
style={{
padding: padding ? padding : "1rem",
textAlign: "center",
@ -70,65 +134,93 @@ function Border({ children, extraClassName, padding }: { children: JSX.Element |
>
<>{children}</>
</div>
);
}
function VBBlock({ opts, block, script }: {
opts: T.TextOptions,
script: "p" | "f",
block: T.VBBasic | T.VBGenNum | (T.VBBasic & {
function VBBlock({
opts,
block,
script,
}: {
opts: T.TextOptions;
script: "p" | "f";
block:
| T.VBBasic
| T.VBGenNum
| (T.VBBasic & {
person: T.Person;
}),
});
}) {
const [length, setLength] = useState<T.Length>("long");
const [version, setVersion] = useState<number>(0);
const ps = getLength(block.ps, length);
function changeVersion() {
setVersion(o => (o + 1) % ps.length);
setVersion((o) => (o + 1) % ps.length);
}
function changeLength() {
setLength(o => (
setLength((o) =>
o === "long"
? "short"
: o === "short" && "mini" in block.ps
? "mini"
: "long"
));
);
}
const infInfo = "gender" in block
const infInfo =
"gender" in block
? getEnglishGenNumInfo(block.gender, block.number)
: "person" in block
? getEnglishPersonInfo(block.person, "short")
: "";
return <div className="text-center">
return (
<div className="text-center">
<div className="d-flex flex-row justify-content-around">
{"long" in block.ps && <div className="clickable small mb-1" onClick={changeLength}>{length}</div>}
{ps.length > 1 && <div className="clickable small mb-1" onClick={changeVersion}>v. {version + 1}</div>}
{"long" in block.ps && (
<div className="clickable small mb-1" onClick={changeLength}>
{length}
</div>
)}
{ps.length > 1 && (
<div className="clickable small mb-1" onClick={changeVersion}>
v. {version + 1}
</div>
)}
</div>
<Border>
<>
{ps[version][script]}
</>
<>{ps[version][script]}</>
</Border>
<div>VBlock</div>
<SubText>{infInfo}</SubText>
</div>
);
}
function WeldedBlock({ opts, welded, script }: {
opts: T.TextOptions,
script: "p" | "f",
welded: T.Welded,
function WeldedBlock({
opts,
welded,
script,
}: {
opts: T.TextOptions;
script: "p" | "f";
welded: T.Welded;
}) {
return <div className="text-center">
<Border padding="0.5rem" extraClassName={script === "p" ? "flex-row-reverse" : ""}>
{welded.left.type === "NComp"
? <NCompBlock opts={opts} comp={welded.left.comp} script={script} />
: welded.left.type === "VB"
? <VBBlock opts={opts} block={welded.left} script={script} />
: <WeldedBlock opts={opts} welded={welded.left} script={script} />}
return (
<div className="text-center">
<Border
padding="0.5rem"
extraClassName={script === "p" ? "flex-row-reverse" : ""}
>
{welded.left.type === "NComp" ? (
<NCompBlock opts={opts} comp={welded.left.comp} script={script} />
) : welded.left.type === "VB" ? (
<VBBlock opts={opts} block={welded.left} script={script} />
) : (
<WeldedBlock opts={opts} welded={welded.left} script={script} />
)}
<VBBlock opts={opts} block={welded.right} script={script} />
</Border>
</div>
);
}
// function VerbSBlock({ opts, v, script }: {
@ -192,19 +284,22 @@ function WeldedBlock({ opts, welded, script }: {
// </div>
// }
function PerfHeadBlock({ opts, ps, script }: {
opts: T.TextOptions,
ps: T.PsString,
script: "p" | "f",
function PerfHeadBlock({
opts,
ps,
script,
}: {
opts: T.TextOptions;
ps: T.PsString;
script: "p" | "f";
}) {
return <div className="text-center">
<Border>
{ps[script]}
</Border>
return (
<div className="text-center">
<Border>{ps[script]}</Border>
<div>perf. head</div>
<SubText>{'\u00A0'}</SubText>
</div>;
<SubText>{"\u00A0"}</SubText>
</div>
);
}
// function ModalAuxBlock({ opts, aux, script }: {
@ -222,249 +317,389 @@ function PerfHeadBlock({ opts, ps, script }: {
// </div>;
// }
function NegBlock({ opts, imperative, script }: {
opts: T.TextOptions,
imperative: boolean,
script: "p" | "f",
function NegBlock({
opts,
imperative,
script,
}: {
opts: T.TextOptions;
imperative: boolean;
script: "p" | "f";
}) {
return <div className="text-center">
return (
<div className="text-center">
<Border>
{negativeParticle[imperative ? "imperative" : "nonImperative"][script]}
</Border>
<div>Neg.</div>
<SubText>{imperative ? "don't" : "not"}</SubText>
</div>;
</div>
);
}
function EquativeBlock({ opts, eq, script }: {
opts: T.TextOptions,
eq: T.EquativeRendered,
script: "p" | "f",
function EquativeBlock({
opts,
eq,
script,
}: {
opts: T.TextOptions;
eq: T.EquativeRendered;
script: "p" | "f";
}) {
const [length, setLength] = useState<T.Length>("long");
function changeLength() {
setLength(o => (
setLength((o) =>
o === "long"
? "short"
: o === "short" && "mini" in eq.ps
? "mini"
: "long"
));
);
}
return <div className="text-center">
{"long" in eq.ps && <div className="clickable small mb-1" onClick={changeLength}>{length}</div>}
<Border>
{getLength(eq.ps, length)[0][script]}
</Border>
return (
<div className="text-center">
{"long" in eq.ps && (
<div className="clickable small mb-1" onClick={changeLength}>
{length}
</div>
)}
<Border>{getLength(eq.ps, length)[0][script]}</Border>
<div>Equative</div>
<SubText>{getEnglishPersonInfo(eq.person, "short")}</SubText>
</div>;
</div>
);
}
function SubjectBlock({ opts, np, role, script }: {
opts: T.TextOptions,
np: T.Rendered<T.NPSelection>,
role: "king" | "servant" | undefined,
script: "p" | "f",
function SubjectBlock({
opts,
np,
role,
script,
}: {
opts: T.TextOptions;
np: T.Rendered<T.NPSelection>;
role: "king" | "servant" | undefined;
script: "p" | "f";
}) {
const english = getEnglishFromRendered(np);
return <div className="text-center">
<div><strong>Subject</strong>{role ? roleIcon[role] : ""}</div>
<NPBlock opts={opts} english={english} script={script}>{np}</NPBlock>
</div>;
return (
<div className="text-center">
<div>
<strong>Subject</strong>
{role ? roleIcon[role] : ""}
</div>
<NPBlock opts={opts} english={english} script={script}>
{np}
</NPBlock>
</div>
);
}
function ObjectBlock({ opts, obj, role, script }: {
opts: T.TextOptions,
obj: T.Rendered<T.ObjectSelectionComplete>["selection"],
role: "king" | "servant" | undefined,
script: "p" | "f",
function ObjectBlock({
opts,
obj,
role,
script,
}: {
opts: T.TextOptions;
obj: T.Rendered<T.ObjectSelectionComplete>["selection"];
role: "king" | "servant" | undefined;
script: "p" | "f";
}) {
if (typeof obj !== "object") {
return null;
}
const english = getEnglishFromRendered(obj);
return <div className="text-center">
<div><strong>Object</strong>{role ? roleIcon[role] : ""}</div>
<NPBlock opts={opts} english={english} script={script}>{obj}</NPBlock>
</div>;
return (
<div className="text-center">
<div>
<strong>Object</strong>
{role ? roleIcon[role] : ""}
</div>
<NPBlock opts={opts} english={english} script={script}>
{obj}
</NPBlock>
</div>
);
}
function NCompBlock({ opts, comp, script }: {
script: "p" | "f",
opts: T.TextOptions,
comp: T.Comp,
function NCompBlock({
opts,
comp,
script,
}: {
script: "p" | "f";
opts: T.TextOptions;
comp: T.Comp;
}) {
return <div className="text-center">
<Border>
{comp.ps[script]}
</Border>
{comp.type === "AdjComp"
? <div>adj. <span className="text-muted small">{getEnglishGenNumInfo(comp.gender, comp.number)}</span></div>
: <div>TODO</div>}
<SubText>
todo
{/* {adj.e} */}
</SubText>
</div>;
return (
<div className="text-center">
<Border>{comp.ps[script]}</Border>
{comp.type === "AdjComp" && (
<div>
<div>
adj.{" "}
<span className="text-muted small">
{getEnglishGenNumInfo(comp.gender, comp.number)}
</span>
</div>
<SubText>{comp.ps.e}</SubText>
</div>
)}
</div>
);
}
function ComplementBlock({ opts, comp, script, inside }: {
script: "p" | "f",
opts: T.TextOptions,
comp: T.Rendered<T.ComplementSelection["selection"]> | T.Rendered<T.UnselectedComplementSelection>["selection"],
inside?: boolean,
function ComplementBlock({
opts,
comp,
script,
inside,
}: {
script: "p" | "f";
opts: T.TextOptions;
comp:
| T.Rendered<T.ComplementSelection["selection"]>
| T.Rendered<T.UnselectedComplementSelection>["selection"];
inside?: boolean;
}) {
function AdjectiveBlock({ opts, adj }: {
opts: T.TextOptions,
adj: T.Rendered<T.AdjectiveSelection>,
function AdjectiveBlock({
opts,
adj,
}: {
opts: T.TextOptions;
adj: T.Rendered<T.AdjectiveSelection>;
}) {
return <div className="text-center">
<Border>
{adj.ps[0][script]}
</Border>
<div>Adj. <span className="text-muted small">({getEnglishParticipleInflection(adj.person, "short")})</span></div>
return (
<div className="text-center">
<Border>{adj.ps[0][script]}</Border>
<div>
Adj.{" "}
<span className="text-muted small">
({getEnglishParticipleInflection(adj.person, "short")})
</span>
</div>
<SubText>{adj.e}</SubText>
</div>;
</div>
);
}
function LocAdvBlock({ opts, adv }: {
opts: T.TextOptions,
adv: T.Rendered<T.LocativeAdverbSelection>,
function LocAdvBlock({
opts,
adv,
}: {
opts: T.TextOptions;
adv: T.Rendered<T.LocativeAdverbSelection>;
}) {
return <div className="text-center">
<Border>
{adv.ps[0][script]}
</Border>
return (
<div className="text-center">
<Border>{adv.ps[0][script]}</Border>
<div>Loc. Adv.</div>
<SubText>{adv.e}</SubText>
</div>;
</div>
);
}
return <div className="text-center">
return (
<div className="text-center">
<div>Complement</div>
{comp.type === "adjective"
? <AdjectiveBlock opts={opts} adj={comp} />
: comp.type === "loc. adv."
? <LocAdvBlock opts={opts} adv={comp} />
: comp.type === "noun"
? <CompNounBlock opts={opts} noun={comp} script={script} />
: comp.type === "unselected"
? <div>
<Border>
____
</Border>
{!inside && <>
{comp.type === "adjective" ? (
<AdjectiveBlock opts={opts} adj={comp} />
) : comp.type === "loc. adv." ? (
<LocAdvBlock opts={opts} adv={comp} />
) : comp.type === "noun" ? (
<CompNounBlock opts={opts} noun={comp} script={script} />
) : comp.type === "unselected" ? (
<div>
<Border>____</Border>
{!inside && (
<>
<div>&nbsp;</div>
<SubText>{comp.e}</SubText>
</>}
</>
)}
</div>
: <div>
) : (
<div>
<Sandwich opts={opts} sandwich={comp} script={script} />
<div>Sandwich</div>
<SubText>{comp.e}</SubText>
</div>}
</div>;
</div>
)}
</div>
);
}
export function APBlock({ opts, children, english, script }: {
opts: T.TextOptions,
children: T.Rendered<T.APSelection>,
english?: string,
script: "p" | "f",
export function APBlock({
opts,
children,
english,
script,
}: {
opts: T.TextOptions;
children: T.Rendered<T.APSelection>;
english?: string;
script: "p" | "f";
}) {
const ap = children;
if (ap.selection.type === "adverb") {
return <div className="text-center">
<Border>
{ap.selection.ps[0][script]}
</Border>
return (
<div className="text-center">
<Border>{ap.selection.ps[0][script]}</Border>
<div>AP</div>
<SubText>{english}</SubText>
</div>;
</div>
);
}
return <div>
return (
<div>
<Sandwich opts={opts} sandwich={ap.selection} script={script} />
<div>AP</div>
<SubText>{english}</SubText>
</div>;
</div>
);
}
function Sandwich({ opts, sandwich, script }: {
opts: T.TextOptions,
sandwich: T.Rendered<T.SandwichSelection<T.Sandwich>>,
script: "p" | "f",
function Sandwich({
opts,
sandwich,
script,
}: {
opts: T.TextOptions;
sandwich: T.Rendered<T.SandwichSelection<T.Sandwich>>;
script: "p" | "f";
}) {
return <div className="text-center">
return (
<div className="text-center">
<div className="text-center">Sandwich 🥪</div>
<Border padding="0.75rem 0.5rem 0.25rem 0.5rem">
<div className={`d-flex flex-row${script === "p" ? "-reverse" : ""} justify-content-between align-items-end`}>
<Possesors opts={opts} script={script}>{sandwich.inside.selection.type !== "pronoun" ? sandwich.inside.selection.possesor : undefined}</Possesors>
<div className="mr-2 ml-1 mb-1"><strong>{sandwich.before ? sandwich.before.f : ""}</strong></div>
<div>
<NPBlock opts={opts} inside script={script}>{sandwich.inside}</NPBlock>
<div
className={`d-flex flex-row${
script === "p" ? "-reverse" : ""
} justify-content-between align-items-end`}
>
<Possesors opts={opts} script={script}>
{sandwich.inside.selection.type !== "pronoun"
? sandwich.inside.selection.possesor
: undefined}
</Possesors>
<div className="mr-2 ml-1 mb-1">
<strong>{sandwich.before ? sandwich.before.f : ""}</strong>
</div>
<div>
<NPBlock opts={opts} inside script={script}>
{sandwich.inside}
</NPBlock>
</div>
<div className="ml-2 mr-1 mb-1">
<strong>{sandwich.after ? sandwich.after.f : ""}</strong>
</div>
<div className="ml-2 mr-1 mb-1"><strong>{sandwich.after ? sandwich.after.f : ""}</strong></div>
</div>
</Border>
</div>;
</div>
);
}
function CompNounBlock({ opts, noun, script }: {
opts: T.TextOptions,
noun: T.Rendered<T.NounSelection>,
script: "p" | "f",
function CompNounBlock({
opts,
noun,
script,
}: {
opts: T.TextOptions;
noun: T.Rendered<T.NounSelection>;
script: "p" | "f";
}) {
return <div className="text-center">
return (
<div className="text-center">
<Border
extraClassName={`!inside && hasPossesor ? "pt-2" : ""`}
padding={"1rem"}
>
{noun.ps[0][script]}
</Border>
<div>
Comp. Noun
</div>
<div>Comp. Noun</div>
<SubText>{noun.e}</SubText>
</div>
);
}
export function NPBlock({ opts, children, inside, english, script }: {
opts: T.TextOptions,
children: T.Rendered<T.NPSelection>,
inside?: boolean,
english?: string,
script: "p" | "f",
export function NPBlock({
opts,
children,
inside,
english,
script,
}: {
opts: T.TextOptions;
children: T.Rendered<T.NPSelection>;
inside?: boolean;
english?: string;
script: "p" | "f";
}) {
const np = children;
const hasPossesor = !!(np.selection.type !== "pronoun" && np.selection.possesor && !np.selection.possesor.shrunken);
const hasPossesor = !!(
np.selection.type !== "pronoun" &&
np.selection.possesor &&
!np.selection.possesor.shrunken
);
const elements = [
...!inside ? [<Possesors opts={opts} script={script}>{np.selection.type !== "pronoun" ? np.selection.possesor : undefined}</Possesors>] : [],
<Adjectives opts={opts} script={script}>{np.selection.adjectives}</Adjectives>,
<div className={np.selection.adjectives?.length ? "mx-1" : ""}> {np.selection.ps[0][script]}</div>,
...(!inside
? [
<Possesors opts={opts} script={script}>
{np.selection.type !== "pronoun"
? np.selection.possesor
: undefined}
</Possesors>,
]
: []),
<Adjectives opts={opts} script={script}>
{np.selection.adjectives}
</Adjectives>,
<div className={np.selection.adjectives?.length ? "mx-1" : ""}>
{" "}
{np.selection.ps[0][script]}
</div>,
];
const el = script === "p" ? elements.reverse() : elements;
return <div className="text-center">
return (
<div className="text-center">
<Border
extraClassName={`!inside && hasPossesor ? "pt-2" : ""`}
padding={inside ? "0.3rem" : hasPossesor ? "0.5rem 0.8rem 0.25rem 0.8rem" : "1rem"}
padding={
inside
? "0.3rem"
: hasPossesor
? "0.5rem 0.8rem 0.25rem 0.8rem"
: "1rem"
}
>
{el}
</Border>
<div className={inside ? "small" : ""}>
NP
{!inside ? <>
{!inside ? (
<>
{` `}
<span className="text-muted small">({getEnglishPersonInfo(np.selection.person, "short")})</span>
</> : <></>}
<span className="text-muted small">
({getEnglishPersonInfo(np.selection.person, "short")})
</span>
</>
) : (
<></>
)}
</div>
{!inside && <SubText>{english}</SubText>}
</div>
);
}
function Possesors({ opts, children, script }: {
opts: T.TextOptions,
children: { shrunken: boolean, np: T.Rendered<T.NPSelection> } | undefined,
script: "p" | "f",
function Possesors({
opts,
children,
script,
}: {
opts: T.TextOptions;
children: { shrunken: boolean; np: T.Rendered<T.NPSelection> } | undefined;
script: "p" | "f";
}) {
if (!children) {
return null;
@ -473,62 +708,107 @@ function Possesors({ opts, children, script }: {
return null;
}
const contraction = checkForContraction(children.np, script);
return <div className={`d-flex flex-row${script === "p" ? "-reverse" : ""} mr-1 align-items-end`} style={{
return (
<div
className={`d-flex flex-row${
script === "p" ? "-reverse" : ""
} mr-1 align-items-end`}
style={{
marginBottom: "0.5rem",
borderBottom: "1px solid grey",
}}>
{children.np.selection.type !== "pronoun" && <Possesors opts={opts} script={script}>{children.np.selection.possesor}</Possesors>}
}}
>
{children.np.selection.type !== "pronoun" && (
<Possesors opts={opts} script={script}>
{children.np.selection.possesor}
</Possesors>
)}
<div>
{contraction && <div className="mb-1">({contraction})</div>}
<div className={classNames("d-flex", (script === "f" ? "flex-row" : "flex-row-reverse"), "align-items-center", { "text-muted": contraction })}>
<div
className={classNames(
"d-flex",
script === "f" ? "flex-row" : "flex-row-reverse",
"align-items-center",
{ "text-muted": contraction }
)}
>
<div className="mx-1 pb-2">{script === "p" ? "د" : "du"}</div>
<div>
<NPBlock script={script} opts={opts} inside>{children.np}</NPBlock>
<NPBlock script={script} opts={opts} inside>
{children.np}
</NPBlock>
</div>
</div>
</div>
</div>
);
}
function Adjectives({ opts, children, script }: {
opts: T.TextOptions,
children: T.Rendered<T.AdjectiveSelection>[] | undefined,
script: "p" | "f",
function Adjectives({
opts,
children,
script,
}: {
opts: T.TextOptions;
children: T.Rendered<T.AdjectiveSelection>[] | undefined;
script: "p" | "f";
}) {
if (!children) {
return null;
}
const c = script === "p"
? children.reverse()
: children;
return <em className="mr-1">
{c.map(a => a.ps[0][script]).join(" ")}{` `}
const c = script === "p" ? children.reverse() : children;
return (
<em className="mr-1">
{c.map((a) => a.ps[0][script]).join(" ")}
{` `}
</em>
);
}
function SubText({ children: e }: { children: string | undefined }) {
return <div className="small text-muted text-center" style={{
return (
<div
className="small text-muted text-center"
style={{
margin: "0 auto",
maxWidth: "300px",
height: "1rem",
}}>{e ? e : ""}</div>;
}}
>
{e ? e : ""}
</div>
);
}
function checkForContraction(np: T.Rendered<T.NPSelection>, script: "p" | "f"): string | undefined {
function checkForContraction(
np: T.Rendered<T.NPSelection>,
script: "p" | "f"
): string | undefined {
if (np.selection.type !== "pronoun") return undefined;
if (np.selection.person === T.Person.FirstSingMale || np.selection.person === T.Person.FirstSingFemale) {
if (
np.selection.person === T.Person.FirstSingMale ||
np.selection.person === T.Person.FirstSingFemale
) {
return script === "f" ? "zmaa" : "زما";
}
if (np.selection.person === T.Person.SecondSingMale || np.selection.person === T.Person.SecondSingFemale) {
if (
np.selection.person === T.Person.SecondSingMale ||
np.selection.person === T.Person.SecondSingFemale
) {
return script === "f" ? "staa" : "ستا";
}
if (np.selection.person === T.Person.FirstPlurMale || np.selection.person === T.Person.FirstPlurFemale) {
if (
np.selection.person === T.Person.FirstPlurMale ||
np.selection.person === T.Person.FirstPlurFemale
) {
return script === "f" ? "zmoonG" : "زمونږ";
}
if (np.selection.person === T.Person.SecondPlurMale || np.selection.person === T.Person.SecondPlurFemale) {
if (
np.selection.person === T.Person.SecondPlurMale ||
np.selection.person === T.Person.SecondPlurFemale
) {
return script === "f" ? "staaso" : "ستاسو";
}
return undefined;
}

44
src/lib/src/diacritics-helpers.test.ts
View File

@ -3,24 +3,20 @@ import {
last,
addP,
lastNonWhitespace,
advanceP,
reverseP,
overwriteP,
advanceForHamza,
advanceForHamzaMid,
} from "./diacritics-helpers";
const phonemeSplits: Array<{
in: string,
out: string[],
in: string;
out: string[];
}> = [
{
in: "kor",
out: ["k", "o", "r"],
},
{
in: "raaghey",
out: ["r", "aa", "gh", "ey"],
in: "raaghay",
out: ["r", "aa", "gh", "ay"],
},
{
in: "ist'imaal",
@ -35,16 +31,16 @@ const phonemeSplits: Array<{
out: ["b", "a"],
},
{
in: "peydáa",
out: ["p", "ey", "d", "aa"],
in: "paydáa",
out: ["p", "ay", "d", "aa"],
},
{
in: "be kaar",
out: ["b", "e", "k", "aa", "r"],
},
{
in: "raadzeyy",
out: ["r", "aa", "dz", "eyy"],
in: "raadzey",
out: ["r", "aa", "dz", "ey"],
},
{
in: "badanuy ??",
@ -68,8 +64,8 @@ phonemeSplits.forEach((s) => {
});
const badPhonetics: Array<{
in: string,
problem: string,
in: string;
problem: string;
}> = [
{
in: "acar",
@ -107,25 +103,31 @@ test("lastNonWhiteSpace should work", () => {
});
test("reverseP should work", () => {
expect(reverseP({
expect(
reverseP({
pIn: "کور",
pOut: "تور ",
})).toEqual({
})
).toEqual({
pIn: " کور",
pOut: "تور",
});
expect(reverseP({
expect(
reverseP({
pIn: "کور",
pOut: "تور ... ",
})).toEqual({
})
).toEqual({
pIn: " ... کور",
pOut: "تور",
});
expect(reverseP({
expect(
reverseP({
pIn: "کور",
pOut: "تور . ",
})).toEqual({
})
).toEqual({
pIn: " . کور",
pOut: "تور",
});
})
});

438
src/lib/src/diacritics-helpers.ts
View File

@ -8,31 +8,62 @@
import { removeAccents } from "./accent-helpers";
export type DiacriticsAccumulator = { pIn: string, pOut: string };
export type DiacriticsAccumulator = { pIn: string; pOut: string };
type Consonant = "b" | "p" | "t" | "T" | "s" | "j" | "ch" | "kh" | "ts" | "dz" | "d" | "D" | "r" | "R" | "z" | "jz" | "G" | "sh" | "x" | "gh" | "f" | "q" | "k" | "g" | "l" | "m" | "n" | "N" | "h" | "w" | "y";
type Ain = "'"
type Consonant =
| "b"
| "p"
| "t"
| "T"
| "s"
| "j"
| "ch"
| "kh"
| "ts"
| "dz"
| "d"
| "D"
| "r"
| "R"
| "z"
| "jz"
| "G"
| "sh"
| "x"
| "gh"
| "f"
| "q"
| "k"
| "g"
| "l"
| "m"
| "n"
| "N"
| "h"
| "w"
| "y";
type Ain = "'";
type JoiningVowel = "-i-" | "-U-" | "-Ul-";
type LongVowel = "aa" | "ee" | "e" | "oo" | "o" | "ey" | "uy" | "eyy";
type LongVowel = "aa" | "ee" | "e" | "oo" | "o" | "ay" | "uy" | "ey";
type ShortVowel = "a" | "i" | "u" | "U";
export type Phoneme = Consonant | Ain | LongVowel | ShortVowel | JoiningVowel;
type PhonemeInfo = {
matches?: string[],
beginningMatches?: string[],
endingMatches?: string[],
consonant?: true,
diacritic?: string,
endingOnly?: true,
takesSukunOnEnding?: true,
longVowel?: true,
canStartWithAynBefore?: true,
useEndingDiacritic?: true,
ainBlendDiacritic?: string,
}
matches?: string[];
beginningMatches?: string[];
endingMatches?: string[];
consonant?: true;
diacritic?: string;
endingOnly?: true;
takesSukunOnEnding?: true;
longVowel?: true;
canStartWithAynBefore?: true;
useEndingDiacritic?: true;
ainBlendDiacritic?: string;
};
export const zwar = "َ";
export const zwarakey = "ٙ";
export const zwarakay = "ٙ";
export const zer = "ِ";
export const pesh = "ُ";
export const sukun = "ْ";
@ -44,128 +75,128 @@ export const fathahan = "ً";
export const phonemeTable: Record<Phoneme, PhonemeInfo> = {
// Consonants
"b": {
b: {
matches: ["ب"],
consonant: true,
},
"p": {
p: {
matches: ["پ"],
consonant: true,
},
"t": {
t: {
matches: ["ت", "ط"],
consonant: true,
},
"T": {
T: {
matches: ["ټ"],
consonant: true,
},
"s": {
s: {
matches: ["س", "ص", "ث"],
consonant: true,
},
"j": {
j: {
matches: ["ج"],
consonant: true,
},
"ch": {
ch: {
matches: ["چ"],
consonant: true,
},
"kh": {
kh: {
matches: ["خ"],
consonant: true,
},
"ts": {
ts: {
matches: ["څ"],
consonant: true,
},
"dz": {
dz: {
matches: ["ځ"],
consonant: true,
},
"d": {
d: {
matches: ["د"],
consonant: true,
},
"D": {
D: {
matches: ["ډ"],
consonant: true,
},
"r": {
r: {
matches: ["ر"],
consonant: true,
},
"R": {
R: {
matches: ["ړ"],
consonant: true,
},
"z": {
z: {
matches: ["ز", "ذ", "ظ", "ض"],
consonant: true,
},
"jz": {
jz: {
matches: ["ژ"],
consonant: true,
},
"G": {
G: {
matches: ["ږ"],
consonant: true,
},
"sh": {
sh: {
matches: ["ش"],
consonant: true,
},
"x": {
x: {
matches: ["ښ"],
consonant: true,
},
"gh": {
gh: {
matches: ["غ"],
consonant: true,
},
"f": {
f: {
matches: ["ف"],
consonant: true,
},
"q": {
q: {
matches: ["ق"],
consonant: true,
},
"k": {
k: {
matches: ["ک"],
consonant: true,
},
"g": {
g: {
matches: ["ګ"],
consonant: true,
},
"l": {
l: {
matches: ["ل"],
consonant: true,
},
"m": {
m: {
matches: ["م"],
consonant: true,
},
"n": {
n: {
matches: ["ن"],
consonant: true,
},
"N": {
N: {
matches: ["ڼ"],
consonant: true,
},
"h": {
h: {
matches: ["ه", "ح"],
consonant: true,
takesSukunOnEnding: true,
},
"w": {
w: {
matches: ["و"],
consonant: true,
},
"y": {
y: {
matches: ["ی"],
consonant: true,
},
@ -175,8 +206,7 @@ export const phonemeTable: Record<Phoneme, PhonemeInfo> = {
consonant: true,
},
// Joining Vowels
"-i-": {
},
"-i-": {},
"-U-": {
matches: [" و ", "و"],
},
@ -184,14 +214,14 @@ export const phonemeTable: Record<Phoneme, PhonemeInfo> = {
matches: ["ال"],
},
// Long Vowels
"aa": {
aa: {
matches: ["ا", "أ"],
beginningMatches: ["آ", "ا"],
endingMatches: ["ا", "یٰ"],
longVowel: true,
ainBlendDiacritic: zwar,
},
"ee": {
ee: {
matches: ["ی"],
longVowel: true,
endingMatches: ["ي"],
@ -199,61 +229,61 @@ export const phonemeTable: Record<Phoneme, PhonemeInfo> = {
canStartWithAynBefore: true,
ainBlendDiacritic: zer,
},
"e": {
e: {
matches: ["ې"],
longVowel: true,
},
"o": {
o: {
matches: ["و"],
longVowel: true,
},
"oo": {
oo: {
matches: ["و"],
longVowel: true,
diacritic: pesh,
useEndingDiacritic: true,
ainBlendDiacritic: pesh,
},
"ey": {
ay: {
matches: ["ی"],
longVowel: true,
endingMatches: ["ی"],
},
"uy": {
uy: {
matches: ["ۍ"],
longVowel: true,
endingOnly: true,
},
"eyy": {
ey: {
matches: ["ئ"],
longVowel: true,
endingOnly: true,
},
// Short Vowels
"a": {
a: {
diacritic: zwar,
endingMatches: ["ه"],
beginningMatches: ["ا", "ع"],
// canComeAfterHeyEnding: true,
// canComeAfterHayEnding: true,
},
"u": {
diacritic: zwarakey,
u: {
diacritic: zwarakay,
endingMatches: ["ه"],
},
"i": {
i: {
diacritic: zer,
endingMatches: ["ه"],
beginningMatches: ["ا", "ع"],
// takesDiacriticBeforeGurdaHeyEnding: true,
// takesDiacriticBeforeGurdaHayEnding: true,
// canBeWasla: true,
},
"U": {
U: {
diacritic: pesh,
endingMatches: ["ه"],
// takesDiacriticBeforeGurdaHeyEnding: true,
// takesDiacriticBeforeGurdaHayEnding: true,
beginningMatches: ["ا", "ع"],
},
}
};
/**
* splits a phonetics string into an array of Phonemes
@ -264,11 +294,55 @@ export const phonemeTable: Record<Phoneme, PhonemeInfo> = {
* @returns an array of phonemes
*/
export function splitFIntoPhonemes(fIn: string): Phoneme[] {
const singleLetterPhonemes: Phoneme[] = ["a", "i", "u", "o", "e", "U", "b", "p", "t", "T", "s", "j", "d", "D", "r", "R", "z", "G", "x", "f", "q", "k", "g", "l", "m", "n", "N", "h", "w", "y", "'"];
const singleLetterPhonemes: Phoneme[] = [
"a",
"i",
"u",
"o",
"e",
"U",
"b",
"p",
"t",
"T",
"s",
"j",
"d",
"D",
"r",
"R",
"z",
"G",
"x",
"f",
"q",
"k",
"g",
"l",
"m",
"n",
"N",
"h",
"w",
"y",
"'",
];
const quadrigraphs: Phoneme[] = ["-Ul-"];
const trigraphs: Phoneme[] = ["eyy", "-i-", "-U-"];
const digraphs: Phoneme[] = ["aa", "ee", "ey", "oo", "kh", "gh", "ts", "dz", "jz", "ch", "sh"];
const trigraphs: Phoneme[] = ["ey", "-i-", "-U-"];
const digraphs: Phoneme[] = [
"aa",
"ee",
"ay",
"oo",
"kh",
"gh",
"ts",
"dz",
"jz",
"ch",
"sh",
];
const endingDigraphs: Phoneme[] = ["uy"];
const willIgnore = ["?", " ", "`", ".", "…", ",", "-"];
@ -276,7 +350,7 @@ export const phonemeTable: Record<Phoneme, PhonemeInfo> = {
const f = removeAccents(fIn).replace(/ă/g, "a");
let index = 0;
while (index < f.length) {
const isLastTwoLetters = (index === f.length - 2 || f[index + 2] === " ");
const isLastTwoLetters = index === f.length - 2 || f[index + 2] === " ";
const threeLetterChunk = f.slice(index, index + 3) as Phoneme;
const fourLetterChunk = f.slice(index, index + 4) as Phoneme;
if (quadrigraphs.includes(fourLetterChunk)) {
@ -313,10 +387,10 @@ export enum PhonemeStatus {
LeadingLongVowel,
LeadingConsonantOrShortVowel,
DoubleConsonantTashdeed,
EndingWithHeyHim,
EndingWithHayHim,
DirectMatch,
DirectMatchAfterSukun,
EndingWithHeyHimFromSukun,
EndingWithHayHimFromSukun,
ShortVowel,
PersianSilentWWithAa,
ArabicWasla,
@ -344,11 +418,16 @@ export enum PhonemeStatus {
EndingSmallH,
}
export function stateInfo({ state, i, phonemes, phoneme }: {
state: DiacriticsAccumulator,
i: number,
phonemes: Phoneme[],
phoneme: Phoneme,
export function stateInfo({
state,
i,
phonemes,
phoneme,
}: {
state: DiacriticsAccumulator;
i: number;
phonemes: Phoneme[];
phoneme: Phoneme;
}) {
const isOutOfWord = (char: string) => !char || char === " ";
const prevPLetter = last(state.pOut);
@ -356,43 +435,86 @@ export function stateInfo({ state, i, phonemes, phoneme }: {
const nextPLetter = state.pIn[1];
const nextPhoneme = phonemes[i + 1];
const previousPhoneme = i > 0 && phonemes[i - 1];
const lastThreePLetters = last(state.pOut, 3) + last(state.pOut, 2) + prevPLetter;
const isBeginningOfWord = (state.pOut === "" || prevPLetter === " ") || (previousPhoneme === "-Ul-" && prevPLetter === "ل") || (["دَر", "وَر"].includes(lastThreePLetters) || (last(state.pOut, 2) + prevPLetter) === "را");
const lastThreePLetters =
last(state.pOut, 3) + last(state.pOut, 2) + prevPLetter;
const isBeginningOfWord =
state.pOut === "" ||
prevPLetter === " " ||
(previousPhoneme === "-Ul-" && prevPLetter === "ل") ||
["دَر", "وَر"].includes(lastThreePLetters) ||
last(state.pOut, 2) + prevPLetter === "را";
const isEndOfWord = isOutOfWord(nextPLetter);
const phonemeInfo = phonemeTable[phoneme];
const previousPhonemeInfo = (!isBeginningOfWord && i > 0) && phonemeTable[phonemes[i-1]];
const previousPhonemeInfo =
!isBeginningOfWord && i > 0 && phonemeTable[phonemes[i - 1]];
// const nextPhoneme = (phonemes.length > (i + 1)) && phonemes[i+1];
// const nextPhonemeInfo = nextPhoneme ? phonemeTable[nextPhoneme] : undefined;
const doubleConsonant = previousPhonemeInfo && (phonemeInfo.consonant && previousPhonemeInfo.consonant);
const needsSukun = (doubleConsonant && ((previousPhoneme !== phoneme) || phonemeInfo.matches?.includes(currentPLetter))) // || (isEndOfWord && phonemeInfo.takesSukunOnEnding);
const useAinBlendDiacritics = (!isBeginningOfWord && (phonemeInfo.ainBlendDiacritic && currentPLetter === "ع"));
const doubleConsonant =
previousPhonemeInfo &&
phonemeInfo.consonant &&
previousPhonemeInfo.consonant;
const needsSukun =
doubleConsonant &&
(previousPhoneme !== phoneme ||
phonemeInfo.matches?.includes(currentPLetter)); // || (isEndOfWord && phonemeInfo.takesSukunOnEnding);
const useAinBlendDiacritics =
!isBeginningOfWord &&
phonemeInfo.ainBlendDiacritic &&
currentPLetter === "ع";
const diacritic = useAinBlendDiacritics
? phonemeInfo.ainBlendDiacritic
: isEndOfWord
? ((!phonemeInfo.longVowel || phonemeInfo.useEndingDiacritic) ? phonemeInfo.diacritic : undefined) : phonemeInfo.diacritic;
? !phonemeInfo.longVowel || phonemeInfo.useEndingDiacritic
? phonemeInfo.diacritic
: undefined
: phonemeInfo.diacritic;
const lastWordEndedW = (char: string) => ((prevPLetter === char && !currentPLetter) || (prevPLetter === " " && last(state.pOut, 2) === char));
const lastWordEndedW = (char: string) =>
(prevPLetter === char && !currentPLetter) ||
(prevPLetter === " " && last(state.pOut, 2) === char);
function getPhonemeState(): PhonemeStatus {
if (isBeginningOfWord && phoneme === "aa" && phonemeInfo.beginningMatches?.includes(currentPLetter)) {
if (
isBeginningOfWord &&
phoneme === "aa" &&
phonemeInfo.beginningMatches?.includes(currentPLetter)
) {
return PhonemeStatus.DirectMatch;
}
if (isBeginningOfWord && phoneme === "oo" && currentPLetter === "و") {
return PhonemeStatus.OoPrefix;
}
if (isBeginningOfWord && (phonemeInfo.longVowel && !phonemeInfo.endingOnly)) {
if (phoneme !== "aa" && currentPLetter !== "ا" && !phonemeInfo.matches?.includes(nextPLetter)) {
if (isBeginningOfWord && phonemeInfo.longVowel && !phonemeInfo.endingOnly) {
if (
phoneme !== "aa" &&
currentPLetter !== "ا" &&
!phonemeInfo.matches?.includes(nextPLetter)
) {
throw Error("phonetics error - needs alef prefix");
}
return PhonemeStatus.LeadingLongVowel;
}
if (isBeginningOfWord && (phonemeInfo.beginningMatches?.includes(currentPLetter) || phonemeInfo.matches?.includes(currentPLetter))) {
if (
isBeginningOfWord &&
(phonemeInfo.beginningMatches?.includes(currentPLetter) ||
phonemeInfo.matches?.includes(currentPLetter))
) {
return PhonemeStatus.LeadingConsonantOrShortVowel;
}
if (isBeginningOfWord && phoneme === "aa" && currentPLetter === "ع" && nextPLetter === "ا") {
if (
isBeginningOfWord &&
phoneme === "aa" &&
currentPLetter === "ع" &&
nextPLetter === "ا"
) {
return PhonemeStatus.AinWithLongAAtBeginning;
}
if (currentPLetter === "ا" && nextPLetter === "ع" && phoneme === "aa" && nextPhoneme !== "'") {
if (
currentPLetter === "ا" &&
nextPLetter === "ع" &&
phoneme === "aa" &&
nextPhoneme !== "'"
) {
return PhonemeStatus.SilentAinAfterAlef;
}
// console.log("------");
@ -400,13 +522,28 @@ export function stateInfo({ state, i, phonemes, phoneme }: {
// console.log("state", state);
// console.log("prevPLetter is space", prevPLetter === " ");
// console.log("------");
if (isBeginningOfWord && phoneme === "u" && prevPLetter === " " && lastNonWhitespace(state.pOut) === "د") {
return PhonemeStatus.EndOfDuParticle
if (
isBeginningOfWord &&
phoneme === "u" &&
prevPLetter === " " &&
lastNonWhitespace(state.pOut) === "د"
) {
return PhonemeStatus.EndOfDuParticle;
}
if (isBeginningOfWord && phoneme === "-Ul-" && currentPLetter === "ا" && nextPLetter === "ل") {
if (
isBeginningOfWord &&
phoneme === "-Ul-" &&
currentPLetter === "ا" &&
nextPLetter === "ل"
) {
return PhonemeStatus.ArabicDefiniteArticleUl;
}
if (phoneme === "a" && nextPhoneme === "'" && phonemes[i+2] === "a" && currentPLetter === "أ") {
if (
phoneme === "a" &&
nextPhoneme === "'" &&
phonemes[i + 2] === "a" &&
currentPLetter === "أ"
) {
return PhonemeStatus.AlefHamzaBeg;
}
if (phoneme === "a" && previousPhoneme === "U" && currentPLetter === "و") {
@ -418,16 +555,35 @@ export function stateInfo({ state, i, phonemes, phoneme }: {
if (phoneme === "'" && currentPLetter === "و" && nextPLetter === "و") {
return PhonemeStatus.GlottalStopBeforeOo;
}
if (phoneme === "oo" && previousPhoneme === "'" && currentPLetter === "و" && prevPLetter === hamzaAbove) {
if (
phoneme === "oo" &&
previousPhoneme === "'" &&
currentPLetter === "و" &&
prevPLetter === hamzaAbove
) {
return PhonemeStatus.OoAfterGlottalStopOo;
}
if (phoneme === "'" && last(state.pOut, 2) === "ع" && isOutOfWord(last(state.pOut, 3))) {
if (
phoneme === "'" &&
last(state.pOut, 2) === "ع" &&
isOutOfWord(last(state.pOut, 3))
) {
return PhonemeStatus.AinBeginningAfterShortVowel;
}
if (!isBeginningOfWord && phoneme === "aa" && currentPLetter === "و" && nextPLetter === "ا") {
if (
!isBeginningOfWord &&
phoneme === "aa" &&
currentPLetter === "و" &&
nextPLetter === "ا"
) {
return PhonemeStatus.PersianSilentWWithAa;
}
if (!isBeginningOfWord && phoneme === "i" && currentPLetter === "ا" && nextPLetter === "ل") {
if (
!isBeginningOfWord &&
phoneme === "i" &&
currentPLetter === "ا" &&
nextPLetter === "ل"
) {
return PhonemeStatus.ArabicWasla;
}
if (phoneme === "-i-" && isBeginningOfWord) {
@ -443,27 +599,47 @@ export function stateInfo({ state, i, phonemes, phoneme }: {
if (phonemeInfo.diacritic && !phonemeInfo.longVowel) {
return PhonemeStatus.ShortAinVowelMissingComma;
}
if ((last(state.pOut, 2) === "ا") && isOutOfWord(last(state.pOut, 3))) {
if (last(state.pOut, 2) === "ا" && isOutOfWord(last(state.pOut, 3))) {
return PhonemeStatus.ShortAinVowelMissingCommaAfterAlefStart;
}
}
if (useAinBlendDiacritics) {
return PhonemeStatus.LongAinVowelMissingComma;
}
if (((!isBeginningOfWord && doubleConsonant) || prevPLetter === " ") && (previousPhoneme === phoneme) && !phonemeInfo.matches?.includes(currentPLetter)) {
if (
((!isBeginningOfWord && doubleConsonant) || prevPLetter === " ") &&
previousPhoneme === phoneme &&
!phonemeInfo.matches?.includes(currentPLetter)
) {
return PhonemeStatus.DoubleConsonantTashdeed;
}
if (phoneme === "aa" && currentPLetter === "ی" && nextPLetter === daggerAlif) {
if (
phoneme === "aa" &&
currentPLetter === "ی" &&
nextPLetter === daggerAlif
) {
return PhonemeStatus.AlefDaggarEnding;
}
if (phoneme === "a" && lastWordEndedW("ح")) {
return PhonemeStatus.ShortAEndingAfterHeem;
}
if (isEndOfWord && ((phoneme === "u" && currentPLetter === "ه") || (phoneme === "h" && ["ه", "ح"].includes(currentPLetter)))) {
return needsSukun ? PhonemeStatus.EndingWithHeyHimFromSukun : PhonemeStatus.EndingWithHeyHim;
if (
isEndOfWord &&
((phoneme === "u" && currentPLetter === "ه") ||
(phoneme === "h" && ["ه", "ح"].includes(currentPLetter)))
) {
return needsSukun
? PhonemeStatus.EndingWithHayHimFromSukun
: PhonemeStatus.EndingWithHayHim;
}
if ((phonemeInfo.matches?.includes(currentPLetter) || (isEndOfWord && phonemeInfo.endingMatches?.includes(currentPLetter)) || (phoneme === "m" && currentPLetter === "ن" && nextPLetter === "ب"))) {
return needsSukun ? PhonemeStatus.DirectMatchAfterSukun : PhonemeStatus.DirectMatch;
if (
phonemeInfo.matches?.includes(currentPLetter) ||
(isEndOfWord && phonemeInfo.endingMatches?.includes(currentPLetter)) ||
(phoneme === "m" && currentPLetter === "ن" && nextPLetter === "ب")
) {
return needsSukun
? PhonemeStatus.DirectMatchAfterSukun
: PhonemeStatus.DirectMatch;
}
if (phonemeInfo.diacritic && !phonemeInfo.longVowel) {
return PhonemeStatus.ShortVowel;
@ -471,21 +647,30 @@ export function stateInfo({ state, i, phonemes, phoneme }: {
if (phoneme === "o" && previousPhoneme === "w" && lastWordEndedW("و")) {
return PhonemeStatus.WoEndingO;
}
if (isEndOfWord && phoneme === "n" && currentPLetter === fathahan && prevPLetter === "ا") {
if (
isEndOfWord &&
phoneme === "n" &&
currentPLetter === fathahan &&
prevPLetter === "ا"
) {
return PhonemeStatus.NOnFathatan;
}
// console.log("errored", "current", phoneme, "next", nextPhoneme);
// console.log("bad phoneme is ", phoneme);
throw new Error("phonetics error - no status found for phoneme: " + phoneme);
throw new Error(
"phonetics error - no status found for phoneme: " + phoneme
);
}
const phs = getPhonemeState();
return {
phs, phonemeInfo, diacritic, prevPLetter,
phs,
phonemeInfo,
diacritic,
prevPLetter,
};
};
}
/**
* returns the nth last character of a string
@ -496,7 +681,10 @@ export function last(s: string, n = 1) {
return s[s.length - n];
}
export function advanceP(state: DiacriticsAccumulator, n: number = 1): DiacriticsAccumulator {
export function advanceP(
state: DiacriticsAccumulator,
n: number = 1
): DiacriticsAccumulator {
return {
pIn: state.pIn.slice(n),
pOut: state.pOut + state.pIn.slice(0, n),
@ -518,14 +706,18 @@ export function reverseP(state: DiacriticsAccumulator): DiacriticsAccumulator {
};
}
export const addP = (toAdd: string | undefined) => (state: DiacriticsAccumulator): DiacriticsAccumulator => {
export const addP =
(toAdd: string | undefined) =>
(state: DiacriticsAccumulator): DiacriticsAccumulator => {
return {
...state,
pOut: toAdd ? (state.pOut + toAdd) : state.pOut,
pOut: toAdd ? state.pOut + toAdd : state.pOut,
};
};
export const overwriteP = (toWrite: string) => (state: DiacriticsAccumulator): DiacriticsAccumulator => {
export const overwriteP =
(toWrite: string) =>
(state: DiacriticsAccumulator): DiacriticsAccumulator => {
return {
pIn: state.pIn.slice(1),
pOut: state.pOut + toWrite,
@ -545,7 +737,10 @@ export function lastNonWhitespace(s: string): string {
return penultimateChar;
}
export function getCurrentNext(state: DiacriticsAccumulator): { current: string, next: string} {
export function getCurrentNext(state: DiacriticsAccumulator): {
current: string;
next: string;
} {
return {
current: state.pIn[0],
next: state.pIn[1],
@ -557,7 +752,9 @@ export function getCurrentNext(state: DiacriticsAccumulator): { current: string,
// return (current === "ع") ? advanceP(state) : state;
// }
export function advanceForHamzaMid(state: DiacriticsAccumulator): DiacriticsAccumulator {
export function advanceForHamzaMid(
state: DiacriticsAccumulator
): DiacriticsAccumulator {
const { current, next } = getCurrentNext(state);
if (current === "ئ" && next && next !== "ئ") {
return advanceP(state);
@ -565,7 +762,9 @@ export function advanceForHamzaMid(state: DiacriticsAccumulator): DiacriticsAccu
return state;
}
export function advanceForHamza(state: DiacriticsAccumulator): DiacriticsAccumulator {
export function advanceForHamza(
state: DiacriticsAccumulator
): DiacriticsAccumulator {
const { current, next } = getCurrentNext(state);
if (current === "ه" && (!next || next === " ")) {
return advanceP(state);
@ -575,4 +774,3 @@ export function advanceForHamza(state: DiacriticsAccumulator): DiacriticsAccumul
// }
return state;
}

100
src/lib/src/diacritics.test.ts
View File

@ -6,23 +6,16 @@
*
*/
import {
addDiacritics,
} from "./diacritics";
import {
zwar,
zwarakey,
sukun,
tashdeed,
} from "./diacritics-helpers";
import { addDiacritics } from "./diacritics";
import { zwar, zwarakay, sukun, tashdeed } from "./diacritics-helpers";
import * as T from "../../types";
const diacriticsSections: {
describe: string,
describe: string;
tests: {
in: T.PsString,
out: string | null,
}[],
in: T.PsString;
out: string | null;
}[];
}[] = [
{
describe: "regular, native Pashto script/sounds",
@ -108,14 +101,14 @@ const diacriticsSections: {
{
in: {
p: "شئ",
f: "sheyy",
f: "shey",
},
out: "شئ",
},
{
in: {
p: "کار کوئ چې لاړ شئ",
f: "kaar kawéyy che laaR sheyy",
f: "kaar kawéy che laaR shey",
},
out: "کار کَوئ چې لاړ شئ",
},
@ -146,28 +139,28 @@ const diacriticsSections: {
p: "کول",
f: "kawul",
},
out: "کَو" + zwarakey + "ل",
out: "کَو" + zwarakay + "ل",
},
{
in: {
p: "کول",
f: "kiwul",
},
out: "کِو" + zwarakey + "ل",
out: "کِو" + zwarakay + "ل",
},
{
in: {
p: "کول",
f: "kUwul",
},
out: "کُو" + zwarakey + "ل",
out: "کُو" + zwarakay + "ل",
},
{
in: {
p: "کول",
f: "kuwul",
},
out: "ک" + zwarakey + "و" + zwarakey + "ل",
out: "ک" + zwarakay + "و" + zwarakay + "ل",
},
{
in: {
@ -200,7 +193,7 @@ const diacriticsSections: {
{
in: {
p: "سپین",
f: "speyn",
f: "spayn",
},
out: "سْپین",
},
@ -272,21 +265,21 @@ const diacriticsSections: {
p: "رغېدل",
f: "raghedul",
},
out: "رَغېد" + zwarakey + "ل",
out: "رَغېد" + zwarakay + "ل",
},
{
in: {
p: "کارول",
f: "kaarawul",
},
out: "کارَو" + zwarakey + "ل",
out: "کارَو" + zwarakay + "ل",
},
{
in: {
p: "پېښېدل",
f: "pexedul",
},
out: "پېښېد" + zwarakey + "ل",
out: "پېښېد" + zwarakay + "ل",
},
{
in: {
@ -298,7 +291,7 @@ const diacriticsSections: {
{
in: {
p: "سړی",
f: "saRey",
f: "saRay",
},
out: "سَړی",
},
@ -335,28 +328,28 @@ const diacriticsSections: {
p: "ایستل",
f: "eestul",
},
out: "اِیسْت" + zwarakey + "ل",
out: "اِیسْت" + zwarakay + "ل",
},
{
in: {
p: "ایستل",
f: "eystul",
f: "aystul",
},
out: "ایسْت" + zwarakey + "ل",
out: "ایسْت" + zwarakay + "ل",
},
{
in: {
p: "اېسېدل",
f: "esedul",
},
out: "اېسېد" + zwarakey + "ل",
out: "اېسېد" + zwarakay + "ل",
},
{
in: {
p: "اوسېدل",
f: "osedul",
},
out: "اوسېد" + zwarakey + "ل",
out: "اوسېد" + zwarakay + "ل",
},
{
in: {
@ -377,7 +370,7 @@ const diacriticsSections: {
p: "واردول",
f: "waaridawul",
},
out: "وارِدَو" + zwarakey + "ل",
out: "وارِدَو" + zwarakay + "ل",
},
{
in: {
@ -557,7 +550,7 @@ const diacriticsSections: {
p: "توجه کول",
f: "tawajU kawul",
},
out: "تَوَجُه کَو" + zwarakey + "ل",
out: "تَوَجُه کَو" + zwarakay + "ل",
},
{
in: {
@ -597,7 +590,7 @@ const diacriticsSections: {
{
in: {
p: "سختسری",
f: "sakht sărey",
f: "sakht săray",
},
out: "سَخْتْسَری",
},
@ -646,7 +639,7 @@ const diacriticsSections: {
{
in: {
p: "وری",
f: "waréy",
f: "waráy",
},
out: "وَری",
},
@ -660,19 +653,20 @@ const diacriticsSections: {
{
in: {
p: "امزری",
f: "umzaréy",
f: "umzaráy",
},
out: zwarakey + "مْزَری",
out: zwarakay + "مْزَری",
},
],
},
{
describe: "ې followed by ی - y needs to be written as e`y to be distinguished from ey - ی",
describe:
"ې followed by ی - y needs to be written as e`y to be distinguished from ay - ی",
tests: [
{
in: {
p: "پتېیل",
f: "pateyúl",
f: "patayúl",
},
out: null,
},
@ -681,14 +675,14 @@ const diacriticsSections: {
p: "پتېیل",
f: "pate`yúl",
},
out: "پَتېی" + zwarakey + "ل",
out: "پَتېی" + zwarakay + "ل",
},
{
in: {
p: "درېیم",
f: "dre`yum",
},
out: "دْرېی" + zwarakey + "م",
out: "دْرېی" + zwarakay + "م",
},
],
},
@ -700,7 +694,7 @@ const diacriticsSections: {
p: "تر ... پورې",
f: "tur ... pore",
},
out: "ت" + zwarakey + "ر ... پورې",
out: "ت" + zwarakay + "ر ... پورې",
},
],
},
@ -729,7 +723,7 @@ const diacriticsSections: {
{
in: {
p: "سړی و",
f: "saRey wo",
f: "saRay wo",
},
out: "سَړی و",
},
@ -811,7 +805,7 @@ const diacriticsSections: {
p: "منبع",
f: "manb'i",
},
out: "مَنْبْعِ"
out: "مَنْبْعِ",
},
{
in: {
@ -825,7 +819,7 @@ const diacriticsSections: {
p: "منبع",
f: "manbi",
},
out: "مَنْبِع"
out: "مَنْبِع",
},
{
in: {
@ -860,7 +854,7 @@ const diacriticsSections: {
p: "مربع جذر",
f: "mUraba' jazúr",
},
out: "مُرَبَع جَذ" + zwarakey + "ر",
out: "مُرَبَع جَذ" + zwarakay + "ر",
},
{
in: {
@ -888,7 +882,7 @@ const diacriticsSections: {
p: "راجع کېدل",
f: "raaji kedul",
},
out: "راجِع کېد" + zwarakey + "ل",
out: "راجِع کېد" + zwarakay + "ل",
},
{
in: {
@ -979,7 +973,7 @@ const diacriticsSections: {
f: "ijmaa'",
},
out: "اِجْماع",
}
},
],
},
{
@ -1064,21 +1058,21 @@ const diacriticsSections: {
p: "د",
f: "du",
},
out: "د" + zwarakey,
out: "د" + zwarakay,
},
{
in: {
p: "د لاس",
f: "du laas",
},
out: "د" + zwarakey + " لاس",
out: "د" + zwarakay + " لاس",
},
{
in: {
p: "د ... په شان",
f: "du ... pu shaan",
},
out: "د" + zwarakey + " ... پهٔ شان",
out: "د" + zwarakay + " ... پهٔ شان",
},
],
},
@ -1097,7 +1091,7 @@ const diacriticsSections: {
p: "ذبح کول",
f: "zabha kawul",
},
out: "ذَبْحَ کَو" + zwarakey + "ل",
out: "ذَبْحَ کَو" + zwarakay + "ل",
},
],
},
@ -1275,14 +1269,14 @@ const diacriticsSections: {
p: "وځم",
f: "oodzum",
},
out: "وُځ" + zwarakey + "م",
out: "وُځ" + zwarakay + "م",
},
{
in: {
p: "وځم",
f: "wUdzum",
},
out: "وُځ" + zwarakey + "م",
out: "وُځ" + zwarakay + "م",
},
],
},
@ -1316,5 +1310,3 @@ test("ending with left over phonetics will throw an error", () => {
addDiacritics({ p: "کار", f: "kaar kawul" });
}).toThrow();
});

225
src/lib/src/diacritics.ts
View File

@ -11,7 +11,7 @@ import {
splitFIntoPhonemes,
Phoneme,
zwar,
zwarakey,
zwarakay,
zer,
pesh,
sukun,
@ -35,10 +35,20 @@ import { pipe } from "rambda";
/**
* Adds diacritics to a given PsString.
* Errors if the phonetics and script don't line up.
*
* IN PROGRESS - This will hopefully get done and replace the messy, unmaintainable phonetics-to-diacritics.ts currently in use
*/
export function addDiacritics({ p, f }: T.PsString, ignoreCommas?: true): T.PsString {
const phonemes: Phoneme[] = splitFIntoPhonemes(!ignoreCommas ? removeFVarients(f) : f);
const { pIn, pOut } = phonemes.reduce(processPhoneme, { pOut: "", pIn: p.trim() });
export function addDiacritics(
{ p, f }: T.PsString,
ignoreCommas?: true
): T.PsString {
const phonemes: Phoneme[] = splitFIntoPhonemes(
!ignoreCommas ? removeFVarients(f) : f
);
const { pIn, pOut } = phonemes.reduce(processPhoneme, {
pOut: "",
pIn: p.trim(),
});
if (pIn !== "") {
throw new Error("phonetics error - phonetics shorter than pashto script");
}
@ -52,159 +62,80 @@ function processPhoneme(
acc: DiacriticsAccumulator,
phoneme: Phoneme,
i: number,
phonemes: Phoneme[],
phonemes: Phoneme[]
): DiacriticsAccumulator {
const state = acc.pIn.slice(0, 5) === " ... "
const state =
acc.pIn.slice(0, 5) === " ... "
? advanceP(acc, 5)
: acc.pIn[0] === " "
? advanceP(acc)
: acc;
const {
phonemeInfo,
diacritic,
phs,
prevPLetter,
} = stateInfo({ state, i, phoneme, phonemes });
const { phonemeInfo, diacritic, phs, prevPLetter } = stateInfo({
state,
i,
phoneme,
phonemes,
});
return (phs === PhonemeStatus.LeadingLongVowel) ?
pipe(
advanceP,
addP(phonemeInfo.diacritic),
advanceP,
)(state)
: (phs === PhonemeStatus.LeadingConsonantOrShortVowel) ?
pipe(
advanceP,
addP(diacritic),
)(state)
: (phs === PhonemeStatus.DoubleConsonantTashdeed) ?
pipe(
prevPLetter === " " ? reverseP : addP(""),
addP(tashdeed)
)(state)
: (phs === PhonemeStatus.EndingWithHeyHim) ?
pipe(
advanceP,
addP(phoneme === "u" ? hamzaAbove : sukun),
)(state)
: (phs === PhonemeStatus.DirectMatch) ?
pipe(
addP(diacritic),
advanceP,
)(state)
: (phs === PhonemeStatus.DirectMatchAfterSukun) ?
pipe(
addP(sukun),
advanceP,
)(state)
: (phs === PhonemeStatus.PersianSilentWWithAa) ?
pipe(
addP("("),
advanceP,
addP(")"),
advanceP,
)(state)
: (phs === PhonemeStatus.ArabicWasla) ?
pipe(
addP(zer),
overwriteP(wasla),
)(state)
: (phs === PhonemeStatus.Izafe) ?
pipe(
reverseP,
addP(zer),
)(state)
: (phs === PhonemeStatus.EndOfDuParticle) ?
pipe(
reverseP,
addP(zwarakey),
)(state)
: (phs === PhonemeStatus.ShortAEndingAfterHeem) ?
pipe(
prevPLetter === " " ? reverseP : addP(""),
addP(zwar),
)(state)
: (phs === PhonemeStatus.EndingWithHeyHimFromSukun) ?
pipe(
addP(sukun),
advanceP,
)(state)
: (phs === PhonemeStatus.AlefDaggarEnding) ?
pipe(
advanceP,
advanceP,
)(state)
: (phs === PhonemeStatus.LongAinVowelMissingComma) ?
pipe(
addP(diacritic),
advanceP,
addP(diacritic)
)(state)
: (phs === PhonemeStatus.ShortAinVowelMissingComma) ?
pipe(
addP(diacritic),
advanceP,
)(state)
: (phs === PhonemeStatus.ShortAinVowelMissingCommaAfterAlefStart) ?
pipe(
advanceP,
advanceP,
)(state)
: (phs === PhonemeStatus.AinWithLongAAtBeginning) ?
pipe(
advanceP,
advanceP,
)(state)
: (phs === PhonemeStatus.AlefWithHamza) ?
pipe(
advanceP,
)(state)
: (phs === PhonemeStatus.ShortVowel) ?
pipe(
return phs === PhonemeStatus.LeadingLongVowel
? pipe(advanceP, addP(phonemeInfo.diacritic), advanceP)(state)
: phs === PhonemeStatus.LeadingConsonantOrShortVowel
? pipe(advanceP, addP(diacritic))(state)
: phs === PhonemeStatus.DoubleConsonantTashdeed
? pipe(prevPLetter === " " ? reverseP : addP(""), addP(tashdeed))(state)
: phs === PhonemeStatus.EndingWithHayHim
? pipe(advanceP, addP(phoneme === "u" ? hamzaAbove : sukun))(state)
: phs === PhonemeStatus.DirectMatch
? pipe(addP(diacritic), advanceP)(state)
: phs === PhonemeStatus.DirectMatchAfterSukun
? pipe(addP(sukun), advanceP)(state)
: phs === PhonemeStatus.PersianSilentWWithAa
? pipe(addP("("), advanceP, addP(")"), advanceP)(state)
: phs === PhonemeStatus.ArabicWasla
? pipe(addP(zer), overwriteP(wasla))(state)
: phs === PhonemeStatus.Izafe
? pipe(reverseP, addP(zer))(state)
: phs === PhonemeStatus.EndOfDuParticle
? pipe(reverseP, addP(zwarakay))(state)
: phs === PhonemeStatus.ShortAEndingAfterHeem
? pipe(prevPLetter === " " ? reverseP : addP(""), addP(zwar))(state)
: phs === PhonemeStatus.EndingWithHayHimFromSukun
? pipe(addP(sukun), advanceP)(state)
: phs === PhonemeStatus.AlefDaggarEnding
? pipe(advanceP, advanceP)(state)
: phs === PhonemeStatus.LongAinVowelMissingComma
? pipe(addP(diacritic), advanceP, addP(diacritic))(state)
: phs === PhonemeStatus.ShortAinVowelMissingComma
? pipe(addP(diacritic), advanceP)(state)
: phs === PhonemeStatus.ShortAinVowelMissingCommaAfterAlefStart
? pipe(advanceP, advanceP)(state)
: phs === PhonemeStatus.AinWithLongAAtBeginning
? pipe(advanceP, advanceP)(state)
: phs === PhonemeStatus.AlefWithHamza
? pipe(advanceP)(state)
: phs === PhonemeStatus.ShortVowel
? pipe(
advanceForHamzaMid,
addP(phonemeInfo.diacritic),
// TODO THIS?
advanceForHamza,
)(state)
: (phs === PhonemeStatus.ShortAForAlefBeforeFathatan) ?
pipe(
advanceP,
)(state)
: (phs === PhonemeStatus.NOnFathatan) ?
pipe(
advanceP,
)(state)
: (phs === PhonemeStatus.HamzaOnWow) ?
pipe(
advanceP,
addP(hamzaAbove),
addP(diacritic),
)(state)
: (phs === PhonemeStatus.ArabicDefiniteArticleUl) ?
pipe(
advanceP,
addP(pesh),
advanceP,
)(state)
: (phs === PhonemeStatus.OoPrefix) ?
pipe(
advanceP,
addP(pesh),
)(state)
: (phs === PhonemeStatus.GlottalStopBeforeOo) ?
pipe(
advanceP,
addP(hamzaAbove),
)(state)
: (phs === PhonemeStatus.OoAfterGlottalStopOo) ?
pipe(
advanceP,
)(state)
: (phs === PhonemeStatus.SilentAinAfterAlef) ?
pipe(
advanceP,
advanceP,
advanceForHamza
)(state)
: phs === PhonemeStatus.ShortAForAlefBeforeFathatan
? pipe(advanceP)(state)
: phs === PhonemeStatus.NOnFathatan
? pipe(advanceP)(state)
: phs === PhonemeStatus.HamzaOnWow
? pipe(advanceP, addP(hamzaAbove), addP(diacritic))(state)
: phs === PhonemeStatus.ArabicDefiniteArticleUl
? pipe(advanceP, addP(pesh), advanceP)(state)
: phs === PhonemeStatus.OoPrefix
? pipe(advanceP, addP(pesh))(state)
: phs === PhonemeStatus.GlottalStopBeforeOo
? pipe(advanceP, addP(hamzaAbove))(state)
: phs === PhonemeStatus.OoAfterGlottalStopOo
? pipe(advanceP)(state)
: phs === PhonemeStatus.SilentAinAfterAlef
? pipe(advanceP, advanceP)(state)
: state;
}

101
src/lib/src/phonetics-to-diacritics.test.ts
View File

@ -11,19 +11,19 @@ import {
splitFIntoPhonemes,
} from "./phonetics-to-diacritics";
const zwarakey = "ٙ";
const zwarakay = "ٙ";
const phonemeSplits: Array<{
in: string,
out: string[],
in: string;
out: string[];
}> = [
{
in: "kor",
out: ["k", "o", "r"],
},
{
in: "raaghey",
out: ["r", "aa", "gh", "ey"],
in: "raaghay",
out: ["r", "aa", "gh", "ay"],
},
{
in: "hatsa",
@ -34,16 +34,16 @@ const phonemeSplits: Array<{
out: ["b", "a"],
},
{
in: "peydáa",
out: ["p", "ey", "d", "áa"],
in: "paydáa",
out: ["p", "ay", "d", "áa"],
},
{
in: "be kaar",
out: ["b", "e", "k", "aa", "r"],
},
{
in: "raadzeyy",
out: ["r", "aa", "dz", "eyy"],
in: "raadzey",
out: ["r", "aa", "dz", "ey"],
},
{
in: "badanuy ??",
@ -67,8 +67,8 @@ phonemeSplits.forEach((s) => {
});
const toTest: Array<{
in: { p: string, f: string },
out: string | undefined,
in: { p: string; f: string };
out: string | undefined;
}> = [
{
in: {
@ -168,28 +168,28 @@ const toTest: Array<{
p: "کول",
f: "kawul",
},
out: "کَو" + zwarakey + "ل",
out: "کَو" + zwarakay + "ل",
},
{
in: {
p: "کول",
f: "kiwul",
},
out: "کِو" + zwarakey + "ل",
out: "کِو" + zwarakay + "ل",
},
{
in: {
p: "کول",
f: "kUwul",
},
out: "کُو" + zwarakey + "ل",
out: "کُو" + zwarakay + "ل",
},
{
in: {
p: "کول",
f: "kuwul",
},
out: "ک" + zwarakey + "و" + zwarakey + "ل",
out: "ک" + zwarakay + "و" + zwarakay + "ل",
},
{
in: {
@ -222,7 +222,7 @@ const toTest: Array<{
{
in: {
p: "سپین",
f: "speyn",
f: "spayn",
},
out: "سْپین",
},
@ -236,7 +236,7 @@ const toTest: Array<{
{
in: {
p: "پېش",
f: "peysh",
f: "paysh",
},
out: undefined,
},
@ -245,33 +245,33 @@ const toTest: Array<{
p: "رغېدل",
f: "raghedul",
},
out: "رَغېد" + zwarakey + "ل",
out: "رَغېد" + zwarakay + "ل",
},
{
in: {
p: "کارول",
f: "kaarawul",
},
out: "کارَو" + zwarakey + "ل",
out: "کارَو" + zwarakay + "ل",
},
{
in: {
p: "پېښېدل",
f: "pexedul",
},
out: "پېښېد" + zwarakey + "ل",
out: "پېښېد" + zwarakay + "ل",
},
{
in: {
p: "مین",
f: "mayín",
f: "ma`yín",
},
out: "مَیِن",
},
{
in: {
p: "سړی",
f: "saRey",
f: "saRay",
},
out: "سَړی",
},
@ -308,28 +308,28 @@ const toTest: Array<{
p: "ایستل",
f: "eestul",
},
out: "اِیسْت" + zwarakey + "ل",
out: "اِیسْت" + zwarakay + "ل",
},
{
in: {
p: "ایستل",
f: "eystul",
f: "aystul",
},
out: "ایسْت" + zwarakey + "ل",
out: "ایسْت" + zwarakay + "ل",
},
{
in: {
p: "اېسېدل",
f: "esedul",
},
out: "اېسېد" + zwarakey + "ل",
out: "اېسېد" + zwarakay + "ل",
},
{
in: {
p: "اوسېدل",
f: "osedul",
},
out: "اوسېد" + zwarakey + "ل",
out: "اوسېد" + zwarakay + "ل",
},
{
in: {
@ -350,7 +350,7 @@ const toTest: Array<{
p: "واردول",
f: "waaridawul",
},
out: "وارِدَو" + zwarakey + "ل",
out: "وارِدَو" + zwarakay + "ل",
},
{
in: {
@ -490,21 +490,21 @@ const toTest: Array<{
p: "ازغن تار",
f: "azghun taar",
},
out: "اَزْغ" + zwarakey + "ن" + " تار",
out: "اَزْغ" + zwarakay + "ن" + " تار",
},
{
in: {
p: "اره څکول",
f: "ara tskawul",
},
out: "اَره څْکَو" + zwarakey + "ل",
out: "اَره څْکَو" + zwarakay + "ل",
},
{
in: {
p: "اږیل",
f: "aGuyúl",
},
out: "اَږ" + zwarakey + "ی" + zwarakey + "ل",
out: "اَږ" + zwarakay + "ی" + zwarakay + "ل",
},
{
in: {
@ -669,7 +669,8 @@ const toTest: Array<{
f: "aadam",
},
out: undefined,
}, {
},
{
in: {
p: "منع",
f: "mán'a",
@ -698,11 +699,11 @@ const toTest: Array<{
},
out: "اسان",
},
// ې followed by ی - y needs to be written as e`y to be distinguished from ey - ی
// ې followed by ی - y needs to be written as e`y to be distinguished from ay - ی
{
in: {
p: "پتېیل",
f: "pateyúl",
f: "patayúl",
},
out: undefined,
},
@ -711,14 +712,14 @@ const toTest: Array<{
p: "پتېیل",
f: "pate`yúl",
},
out: "پَتېی" + zwarakey + "ل",
out: "پَتېی" + zwarakay + "ل",
},
{
in: {
p: "درېیم",
f: "dre`yum",
},
out: "دْرېی" + zwarakey + "م",
out: "دْرېی" + zwarakay + "م",
},
{
in: {
@ -733,7 +734,7 @@ const toTest: Array<{
p: "تر ... پورې",
f: "tur ... pore",
},
out: "ت" + zwarakey + "ر ... پورې",
out: "ت" + zwarakay + "ر ... پورې",
},
// joiner و
{
@ -763,21 +764,21 @@ const toTest: Array<{
p: "د",
f: "du",
},
out: "د" + zwarakey,
out: "د" + zwarakay,
},
{
in: {
p: "د لاس",
f: "du laas",
},
out: "د" + zwarakey + " لاس",
out: "د" + zwarakay + " لاس",
},
{
in: {
p: "د ... په شان",
f: "du ... pu shaan",
},
out: "د" + zwarakey + " ... پهٔ شان",
out: "د" + zwarakay + " ... پهٔ شان",
},
{
in: {
@ -798,7 +799,7 @@ const toTest: Array<{
p: "ذبح کول",
f: "zabha kawul",
},
out: "ذَبْحَ کَو" + zwarakey + "ل",
out: "ذَبْحَ کَو" + zwarakay + "ل",
},
// require dagger alif on words ending with یٰ
{
@ -864,7 +865,7 @@ const toTest: Array<{
p: "طمع لرل",
f: "tama larul",
},
out: "طَمعَ لَر" + zwarakey + "ل",
out: "طَمعَ لَر" + zwarakay + "ل",
},
// Ua ؤ
{
@ -885,7 +886,7 @@ const toTest: Array<{
{
in: {
p: "شئ",
f: "sheyy",
f: "shey",
},
out: "شئ",
},
@ -900,7 +901,7 @@ const toTest: Array<{
{
in: {
p: "سړی و",
f: "saRey wo",
f: "saRay wo",
},
out: "سَړی و",
},
@ -938,7 +939,7 @@ const toTest: Array<{
p: "توجه کول",
f: "tawajU kawul",
},
out: "تَوَجُه کَو" + zwarakey + "ل",
out: "تَوَجُه کَو" + zwarakay + "ل",
},
// With Arabic definate article -Ul- ال
{
@ -975,7 +976,7 @@ const toTest: Array<{
p: "راجع کېدل",
f: "raaji kedul",
},
out: "راجعِ کېد" + zwarakey + "ل",
out: "راجعِ کېد" + zwarakay + "ل",
},
{
in: {
@ -987,7 +988,7 @@ const toTest: Array<{
{
in: {
p: "سختسری",
f: "sakht sărey",
f: "sakht săray",
},
out: "سَخْتْسَری",
},
@ -1042,7 +1043,7 @@ const toTest: Array<{
p: "مربع جذر",
f: "mUraba' jazúr",
},
out: "مُرَبَع جَذ" + zwarakey + "ر",
out: "مُرَبَع جَذ" + zwarakay + "ر",
},
{
in: {
@ -1101,14 +1102,14 @@ const toTest: Array<{
p: "وځم",
f: "oodzum",
},
out: "وځ" + zwarakey + "م",
out: "وځ" + zwarakay + "م",
},
{
in: {
p: "وځم",
f: "wUdzum",
},
out: "وُځ" + zwarakey + "م",
out: "وُځ" + zwarakay + "م",
},
];

449
src/lib/src/phonetics-to-diacritics.ts
View File

@ -7,7 +7,7 @@
*/
const zwar = "َ";
const zwarakey = "ٙ";
const zwarakay = "ٙ";
const zer = "ِ";
const pesh = "ُ";
const sukun = "ْ";
@ -19,8 +19,25 @@ const fathahan = "ً";
// TODO: THESE OTHER TRIGRAPHS??
const quadrigraphs = ["-Ul-"];
const trigraphs = ["eyy", "éyy", "-i-", "-U-"]; // , "aay", "áay", "ooy", "óoy"];
const digraphs = ["ắ", "aa", "áa", "ee", "ée", "ey", "éy", "oo", "óo", "kh", "gh", "ts", "dz", "jz", "ch", "sh"];
const trigraphs = ["ey", "éy", "-i-", "-U-"]; // , "aay", "áay", "ooy", "óoy"];
const digraphs = [
"ắ",
"aa",
"áa",
"ee",
"ée",
"ay",
"áy",
"oo",
"óo",
"kh",
"gh",
"ts",
"dz",
"jz",
"ch",
"sh",
];
const endingDigraphs = ["uy", "úy"];
const willIgnore = ["?", " ", "`", ".", "…"];
@ -28,7 +45,7 @@ export function splitFIntoPhonemes(f: string): string[] {
const result: string[] = [];
let index = 0;
while (index < f.length) {
const isLastTwoLetters = (index === f.length - 2 || f[index + 2] === " ");
const isLastTwoLetters = index === f.length - 2 || f[index + 2] === " ";
const threeLetterChunk = f.slice(index, index + 3);
const fourLetterChunk = f.slice(index, index + 4);
if (quadrigraphs.includes(fourLetterChunk)) {
@ -89,7 +106,12 @@ const phonemeTable = [
{ phoneme: "m", possibilities: ["م"], consonant: true },
{ phoneme: "n", possibilities: ["ن"], consonant: true },
{ phoneme: "N", possibilities: ["ڼ"], consonant: true },
{ phoneme: "h", possibilities: ["ه", "ح"], consonant: true, takesSukunOnEnding: true },
{
phoneme: "h",
possibilities: ["ه", "ح"],
consonant: true,
takesSukunOnEnding: true,
},
{ phoneme: "w", possibilities: ["و"], consonant: true },
{ phoneme: "y", possibilities: ["ی"], consonant: true },
@ -99,33 +121,130 @@ const phonemeTable = [
{ phoneme: "-Ul-", possibilities: ["ال"] },
// vowels
{ phoneme: "aa", possibilities: ["ا"], beginning: ["آ", "ا"], endingPossibilities: ["ا", "یٰ"], isLongA: true, canStartWithAynBefore: true },
{ phoneme: "áa", possibilities: ["ا"], beginning: ["آ", "ا"], endingPossibilities: ["ا", "یٰ"], isLongA: true, canStartWithAynBefore: true },
{ phoneme: "ee", possibilities: ["ی"], addAlefOnBeginning: true, endingPossibilities: ["ي"], diacritic: zer, canStartWithAynBefore: true },
{ phoneme: "ée", possibilities: ["ی"], addAlefOnBeginning: true, endingPossibilities: ["ي"], diacritic: zer, canStartWithAynBefore: true },
{
phoneme: "aa",
possibilities: ["ا"],
beginning: ["آ", "ا"],
endingPossibilities: ["ا", "یٰ"],
isLongA: true,
canStartWithAynBefore: true,
},
{
phoneme: "áa",
possibilities: ["ا"],
beginning: ["آ", "ا"],
endingPossibilities: ["ا", "یٰ"],
isLongA: true,
canStartWithAynBefore: true,
},
{
phoneme: "ee",
possibilities: ["ی"],
addAlefOnBeginning: true,
endingPossibilities: ["ي"],
diacritic: zer,
canStartWithAynBefore: true,
},
{
phoneme: "ée",
possibilities: ["ی"],
addAlefOnBeginning: true,
endingPossibilities: ["ي"],
diacritic: zer,
canStartWithAynBefore: true,
},
{ phoneme: "e", possibilities: ["ې"], addAlefOnBeginning: true },
{ phoneme: "é", possibilities: ["ې"], addAlefOnBeginning: true },
{ phoneme: "o", possibilities: ["و"], addAlefOnBeginning: true },
{ phoneme: "ó", possibilities: ["و"], addAlefOnBeginning: true },
{ phoneme: "oo", possibilities: ["و"], addAlefOnBeginning: true, alsoCanBePrefix: true, diacritic: pesh },
{ phoneme: "óo", possibilities: ["و"], addAlefOnBeginning: true, diacritic: pesh },
{ phoneme: "ey", possibilities: ["ی"], addAlefOnBeginning: true, endingPossibilities: ["ی"]},
{ phoneme: "éy", possibilities: ["ی"], addAlefOnBeginning: true, endingPossibilities: ["ی"]},
{
phoneme: "oo",
possibilities: ["و"],
addAlefOnBeginning: true,
alsoCanBePrefix: true,
diacritic: pesh,
},
{
phoneme: "óo",
possibilities: ["و"],
addAlefOnBeginning: true,
diacritic: pesh,
},
{
phoneme: "ay",
possibilities: ["ی"],
addAlefOnBeginning: true,
endingPossibilities: ["ی"],
},
{
phoneme: "áy",
possibilities: ["ی"],
addAlefOnBeginning: true,
endingPossibilities: ["ی"],
},
{ phoneme: "uy", possibilities: ["ۍ"], endingOnly: true },
{ phoneme: "úy", possibilities: ["ۍ"], endingOnly: true }, // THIS CAN ONLY COME AT THE END DEAL WITH THIS
{ phoneme: "eyy", possibilities: ["ئ"], endingOnly: true },
{ phoneme: "éyy", possibilities: ["ئ"], endingOnly: true },
{ phoneme: "ey", possibilities: ["ئ"], endingOnly: true },
{ phoneme: "éy", possibilities: ["ئ"], endingOnly: true },
{ phoneme: "a", diacritic: zwar, endingPossibilities: ["ه"], canComeAfterHeyEnding: true, canBeFirstPartOfFathahanEnding: true },
{ phoneme: "á", diacritic: zwar, endingPossibilities: ["ه"], canComeAfterHeyEnding: true, canBeFirstPartOfFathahanEnding: true },
{
phoneme: "a",
diacritic: zwar,
endingPossibilities: ["ه"],
canComeAfterHayEnding: true,
canBeFirstPartOfFathahanEnding: true,
},
{
phoneme: "á",
diacritic: zwar,
endingPossibilities: ["ه"],
canComeAfterHayEnding: true,
canBeFirstPartOfFathahanEnding: true,
},
{ phoneme: "ă", diacritic: zwar },
{ phoneme: "ắ", diacritic: zwar },
{ phoneme: "u", diacritic: zwarakey, endingPossibilities: ["ه"], hamzaOnEnd: true },
{ phoneme: "ú", diacritic: zwarakey, endingPossibilities: ["ه"], hamzaOnEnd: true },
{ phoneme: "i", diacritic: zer, endingPossibilities: ["ه"], takesDiacriticBeforeGurdaHeyEnding: true, canBeWasla: true, beginning: ["ا", "ع"] },
{ phoneme: "í", diacritic: zer, endingPossibilities: ["ه"], takesDiacriticBeforeGurdaHeyEnding: true, canBeWasla: true, beginning: ["ا", "ع"] },
{ phoneme: "U", diacritic: pesh, endingPossibilities: ["ه"], takesDiacriticBeforeGurdaHeyEnding: true, beginning: ["ا", "ع"] },
{ phoneme: "Ú", diacritic: pesh, endingPossibilities: ["ه"], takesDiacriticBeforeGurdaHeyEnding: true, beginning: ["ا", "ع"] },
{
phoneme: "u",
diacritic: zwarakay,
endingPossibilities: ["ه"],
hamzaOnEnd: true,
},
{
phoneme: "ú",
diacritic: zwarakay,
endingPossibilities: ["ه"],
hamzaOnEnd: true,
},
{
phoneme: "i",
diacritic: zer,
endingPossibilities: ["ه"],
takesDiacriticBeforeGurdaHayEnding: true,
canBeWasla: true,
beginning: ["ا", "ع"],
},
{
phoneme: "í",
diacritic: zer,
endingPossibilities: ["ه"],
takesDiacriticBeforeGurdaHayEnding: true,
canBeWasla: true,
beginning: ["ا", "ع"],
},
{
phoneme: "U",
diacritic: pesh,
endingPossibilities: ["ه"],
takesDiacriticBeforeGurdaHayEnding: true,
beginning: ["ا", "ع"],
},
{
phoneme: "Ú",
diacritic: pesh,
endingPossibilities: ["ه"],
takesDiacriticBeforeGurdaHayEnding: true,
beginning: ["ا", "ع"],
},
];
function isSpace(s: string): boolean {
@ -142,7 +261,11 @@ interface IDiacriticsErrorMessage {
i: number;
}
function possibilityMatches(p: string, pIndex: number, possibilities: string[] | undefined): boolean {
function possibilityMatches(
p: string,
pIndex: number,
possibilities: string[] | undefined
): boolean {
/* istanbul ignore next */
if (!possibilities) {
return false;
@ -155,10 +278,15 @@ function possibilityMatches(p: string, pIndex: number, possibilities: string[] |
return false;
}
function isPrefixedByDirectionalPronoun(i: number, phonemes: string[]): boolean {
function isPrefixedByDirectionalPronoun(
i: number,
phonemes: string[]
): boolean {
const potentialPronounFourCharSlice = phonemes.slice(i - 4, i).join("");
const potentialPronounThreeCharSlice = phonemes.slice(i - 3, i).join("");
if (["wăr-", "war-", "dăr-", "dar-"].includes(potentialPronounFourCharSlice)) {
if (
["wăr-", "war-", "dăr-", "dar-"].includes(potentialPronounFourCharSlice)
) {
return true;
}
if (potentialPronounThreeCharSlice === "raa-") {
@ -167,7 +295,11 @@ function isPrefixedByDirectionalPronoun(i: number, phonemes: string[]): boolean
return false;
}
export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes: boolean = false): string | undefined {
export function phoneticsToDiacritics(
ps: string,
ph: string,
forbidOoPrefixes: boolean = false
): string | undefined {
const phonemes = splitFIntoPhonemes(ph.trim().split(",")[0]);
const p = ps.trim();
let result = "";
@ -179,58 +311,72 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
if (phoneme === "-") {
return;
}
const phonemeInfo = phonemeTable.find((element) => element.phoneme === phoneme);
const phonemeInfo = phonemeTable.find(
(element) => element.phoneme === phoneme
);
if (!phonemeInfo) {
errored.push({ error: "phoneme info not found", phoneme, i });
return;
}
const isDoubleConsonant = (
const isDoubleConsonant =
phonemeInfo.consonant &&
phoneme === phonemes[i - 1] &&
// TODO: is this thourough enough to allow double consonants on the ending of the previous word?
!(isSpace(p[pIndex - 1]) && phonemeInfo.possibilities.includes(p[pIndex])) // avoid false double consonant ie ازل لیک azalleek
) ? true : false;
const isBeginning = !isDoubleConsonant && ((i === 0) || isSpace(p[pIndex - 1]) || (phonemes[i - 1] === "-Ul-") || isPrefixedByDirectionalPronoun(i, phonemes));
const upcomingAEndingAfterHey = (p[pIndex] === "ح" && isSpace(p[pIndex + 1]) && ["a", "á"].includes(phonemes[i + 1]));
? true
: false;
const isBeginning =
!isDoubleConsonant &&
(i === 0 ||
isSpace(p[pIndex - 1]) ||
phonemes[i - 1] === "-Ul-" ||
isPrefixedByDirectionalPronoun(i, phonemes));
const upcomingAEndingAfterHay =
p[pIndex] === "ح" &&
isSpace(p[pIndex + 1]) &&
["a", "á"].includes(phonemes[i + 1]);
// TODO: break this into a seperate function -- why can it sometimes be set to undefined?
const isEnding = (i === phonemes.length - 1) || ((
(phonemeInfo.possibilities && isSpace(p[pIndex + 1])) ||
const isEnding =
i === phonemes.length - 1 ||
(((phonemeInfo.possibilities && isSpace(p[pIndex + 1])) ||
(!phonemeInfo.possibilities && isSpace(p[pIndex])) ||
(
(!phonemeInfo.possibilities && isSpace(p[pIndex + 1])) &&
(possibilityMatches(p, pIndex, phonemeInfo.endingPossibilities) || (p[pIndex] === "ع" && phonemes[i + 1] !== "'"))
)
) && !upcomingAEndingAfterHey
&& // makes sure the next letter isn't a double consonant like haqq <-
(!phonemeInfo.possibilities &&
isSpace(p[pIndex + 1]) &&
(possibilityMatches(p, pIndex, phonemeInfo.endingPossibilities) ||
(p[pIndex] === "ع" && phonemes[i + 1] !== "'")))) &&
!upcomingAEndingAfterHay && // makes sure the next letter isn't a double consonant like haqq <-
!(
phonemeInfo.consonant && phoneme === phonemes[i + 1] // &&
(phonemeInfo.consonant && phoneme === phonemes[i + 1]) // &&
// !(isSpace(p[pIndex + 1]) && phonemeInfo.possibilities.includes(p[pIndex]))
)
) || // can be the trailing double consanant on the end of a word
(
phonemeInfo.consonant && phoneme === phonemes[i - 1] &&
!(isEndSpace(p[pIndex - 1]) && phonemeInfo.possibilities.includes(p[pIndex]))
) || // can be یٰ ending
(
isEndSpace(p[pIndex + 2]) && (p.slice(pIndex, pIndex + 2) === "یٰ")
);
)) || // can be the trailing double consanant on the end of a word
(phonemeInfo.consonant &&
phoneme === phonemes[i - 1] &&
!(
isEndSpace(p[pIndex - 1]) &&
phonemeInfo.possibilities.includes(p[pIndex])
)) || // can be یٰ ending
(isEndSpace(p[pIndex + 2]) && p.slice(pIndex, pIndex + 2) === "یٰ");
const isUofDu = phoneme === "u" && (
p.slice(pIndex - 2, pIndex) === "د " || // د as previous word
const isUofDu =
phoneme === "u" &&
(p.slice(pIndex - 2, pIndex) === "د " || // د as previous word
(p[pIndex] === undefined && p[pIndex - 1] === "د") || // د as the whole thing
p.slice(pIndex - 6, pIndex) === "د ... " // ... د is as the previous word
);
p.slice(pIndex - 6, pIndex) === "د ... "); // ... د is as the previous word
// TODO: Should p[pIndex - 1] also be in there ??? It messed up قطعه for instance
const isEndingAynVowel = isEnding && phonemeInfo.diacritic && [p[pIndex], p[pIndex - 1]].includes("ع") && p[pIndex] !== "ه";
const isEndingAynVowel =
isEnding &&
phonemeInfo.diacritic &&
[p[pIndex], p[pIndex - 1]].includes("ع") &&
p[pIndex] !== "ه";
const isMiddle = !isBeginning && !isEnding;
const isSilentWaw = (
const isSilentWaw =
p[pIndex] === "و" &&
p[pIndex - 1] === "خ" &&
p[pIndex + 1] === "ا" &&
["áa", "aa"].includes(phoneme)
);
const isAnAEndingAfterHey = isEnding && p[pIndex - 1] === "ح" && phonemeInfo.canComeAfterHeyEnding;
["áa", "aa"].includes(phoneme);
const isAnAEndingAfterHay =
isEnding && p[pIndex - 1] === "ح" && phonemeInfo.canComeAfterHayEnding;
if (isDoubleConsonant) {
pIndex--;
if (isSpace(p[pIndex])) {
@ -247,14 +393,22 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
pIndex++;
}
// special check for Arabic wasla
if (p.slice(0, 3) === "بال" && phonemes[i - 1] === "b" && phonemeInfo.canBeWasla && phonemes[i + 1] === "l") {
if (
p.slice(0, 3) === "بال" &&
phonemes[i - 1] === "b" &&
phonemeInfo.canBeWasla &&
phonemes[i + 1] === "l"
) {
result += phonemeInfo.diacritic + wasla;
pIndex++;
previousPhonemeWasAConsonant = false;
return;
}
// special check for fathahan ending
if (phonemeInfo.canBeFirstPartOfFathahanEnding && p.slice(pIndex, pIndex + 2) === "اً") {
if (
phonemeInfo.canBeFirstPartOfFathahanEnding &&
p.slice(pIndex, pIndex + 2) === "اً"
) {
result += "ا";
pIndex++;
return;
@ -265,7 +419,12 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
return;
}
// special check for words starting with عا or عی
if (isBeginning && phonemeInfo.canStartWithAynBefore && p[pIndex] === "ع" && phonemeInfo.possibilities.includes(p[pIndex + 1])) {
if (
isBeginning &&
phonemeInfo.canStartWithAynBefore &&
p[pIndex] === "ع" &&
phonemeInfo.possibilities.includes(p[pIndex + 1])
) {
result += "ع";
result += phonemeInfo.diacritic ? phonemeInfo.diacritic : "";
result += p[pIndex + 1];
@ -273,23 +432,45 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
return;
}
// special check for ؤ Ua
if (phoneme === "U" && phonemes[i + 1] === "a" && phonemes[i + 2] !== "a" && p[pIndex] === "و") {
if (
phoneme === "U" &&
phonemes[i + 1] === "a" &&
phonemes[i + 2] !== "a" &&
p[pIndex] === "و"
) {
result += "ؤ";
pIndex++;
return;
}
if (phoneme === "a" && phonemes[i - 1] === "U" && phonemes[i + 1] !== "a" && result.slice(-2) === "ؤ") {
if (
phoneme === "a" &&
phonemes[i - 1] === "U" &&
phonemes[i + 1] !== "a" &&
result.slice(-2) === "ؤ"
) {
previousPhonemeWasAConsonant = false;
return;
}
// special check for و wo
if (isBeginning && phoneme === "w" && phonemes[i + 1] === "o" && p[pIndex] === "و" && isEndSpace(p[pIndex + 1])) {
if (
isBeginning &&
phoneme === "w" &&
phonemes[i + 1] === "o" &&
p[pIndex] === "و" &&
isEndSpace(p[pIndex + 1])
) {
result += "و";
pIndex++;
return;
}
// TODO: isEndSpace here is redundant??
if (isEnding && phoneme === "o" && phonemes[i - 1] === "w" && p[pIndex - 1] === "و" && isEndSpace(p[pIndex])) {
if (
isEnding &&
phoneme === "o" &&
phonemes[i - 1] === "w" &&
p[pIndex - 1] === "و" &&
isEndSpace(p[pIndex])
) {
pIndex++;
return;
}
@ -300,38 +481,67 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
return;
}
// special check for for أ in the middle of the word
if (!isBeginning && p[pIndex] === "أ" && phoneme === "a" && phonemes[i + 1] === "'" && phonemes[i + 2] === "a") {
if (
!isBeginning &&
p[pIndex] === "أ" &&
phoneme === "a" &&
phonemes[i + 1] === "'" &&
phonemes[i + 2] === "a"
) {
result += "أ";
pIndex++;
return;
}
if (p[pIndex - 1] === "أ" && phonemes[i - 1] === "a" && phoneme === "'" && phonemes[i + 1] === "a") {
if (
p[pIndex - 1] === "أ" &&
phonemes[i - 1] === "a" &&
phoneme === "'" &&
phonemes[i + 1] === "a"
) {
return;
}
if (p[pIndex - 1] === "أ" && phonemes[i - 2] === "a" && phonemes[i - 1] === "'" && phoneme === "a") {
if (
p[pIndex - 1] === "أ" &&
phonemes[i - 2] === "a" &&
phonemes[i - 1] === "'" &&
phoneme === "a"
) {
previousPhonemeWasAConsonant = false;
return;
}
// special check for وو 'oo
if (!isBeginning && p[pIndex] === "و" && p[pIndex + 1] === "و" && phoneme === "'" && phonemes[i + 1] === "oo") {
if (
!isBeginning &&
p[pIndex] === "و" &&
p[pIndex + 1] === "و" &&
phoneme === "'" &&
phonemes[i + 1] === "oo"
) {
result += "وُو";
pIndex += 2;
return;
}
if (p[pIndex - 2] === "و" && p[pIndex - 1] === "و" && phonemes[i - 1] === "'" && phoneme === "oo") {
if (
p[pIndex - 2] === "و" &&
p[pIndex - 1] === "و" &&
phonemes[i - 1] === "'" &&
phoneme === "oo"
) {
previousPhonemeWasAConsonant = false;
return;
}
const prevLetterWasBeginningAyn = (
const prevLetterWasBeginningAyn =
p[pIndex - 1] === "ع" &&
// isEndSpace(p[pIndex]) && // This breaks it
phoneme === "'"
);
phoneme === "'";
// check if the phoneme lines up in the Pashto word
if (isBeginning && !isUofDu && phonemeInfo.addAlefOnBeginning) {
// TODO: Maybe a little bad because it doesn't loop through possibilities
if ((!phonemeInfo.alsoCanBePrefix || forbidOoPrefixes) && p.slice(pIndex, pIndex + 2) !== "ا" + phonemeInfo.possibilities[0]) {
if (
(!phonemeInfo.alsoCanBePrefix || forbidOoPrefixes) &&
p.slice(pIndex, pIndex + 2) !== "ا" + phonemeInfo.possibilities[0]
) {
errored.push({ error: "didn't start with an aleph", phoneme, i });
return;
}
@ -348,18 +558,18 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
pIndex++;
return;
} else if (
(isEnding && phonemeInfo.endingPossibilities) &&
isEnding &&
phonemeInfo.endingPossibilities &&
!isUofDu &&
(
!possibilityMatches(p, pIndex, phonemeInfo.endingPossibilities) &&
!isEndingAynVowel && // allowing short vowels on the end of words ending with ع
!isAnAEndingAfterHey
)
!isAnAEndingAfterHay
) {
errored.push({ error: "bad ending", phoneme, i });
return;
} else if (
(isEnding && !phonemeInfo.endingPossibilities) &&
isEnding &&
!phonemeInfo.endingPossibilities &&
phonemeInfo.possibilities &&
!phonemeInfo.possibilities.includes(p[pIndex])
) {
@ -367,14 +577,17 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
errored.push({ error: "bad ending 2", phoneme, i });
return;
} else if (
(phonemeInfo.possibilities && !isEnding) &&
(
!(phonemeInfo.possibilities.includes(p[pIndex])) &&
!(p[pIndex] === "ن" && (p[pIndex + 1] === "ب" && phoneme === "m")) && // && // exception case with نب === mb
phonemeInfo.possibilities &&
!isEnding &&
!phonemeInfo.possibilities.includes(p[pIndex]) &&
!(p[pIndex] === "ن" && p[pIndex + 1] === "ب" && phoneme === "m") && // && // exception case with نب === mb
!prevLetterWasBeginningAyn // exception case with words starting with ع like i'zzat
)
) {
errored.push({ error: "improper coressponding letter in middle of word", phoneme, i });
errored.push({
error: "improper coressponding letter in middle of word",
phoneme,
i,
});
return;
}
// console.log(phoneme, pIndex, p[pIndex], isEnding);
@ -382,7 +595,12 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
// OK, it lines up with the Pashto word, we're good
// Now continue building the result string
// deal with starting with short vowels and alef
if (!isUofDu && isBeginning && !phonemeInfo.possibilities && !phonemeInfo.isIzafe) {
if (
!isUofDu &&
isBeginning &&
!phonemeInfo.possibilities &&
!phonemeInfo.isIzafe
) {
// TODO: WHY IS THIS HERE
if (!["ا", "ع"].includes(p[pIndex])) {
errored.push({ error: "bad beginning 2", phoneme, i });
@ -392,22 +610,30 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
pIndex++;
}
// if the phoneme carries a diacritic insert it (before the letter if it's coming)
const isOoPrefix = (phonemeInfo.alsoCanBePrefix && isBeginning && (p[pIndex - 1] !== "ا"));
const isOoPrefix =
phonemeInfo.alsoCanBePrefix && isBeginning && p[pIndex - 1] !== "ا";
if (phonemeInfo.diacritic && !isEnding && !isOoPrefix) {
// using this hack to remove the space and put it after the zwarakey we're going to add after د
// using this hack to remove the space and put it after the zwarakay we're going to add after د
if (isUofDu && result.slice(-5) === " ... ") {
result = result.slice(0, -5) + zwarakey + " ... ";
result = result.slice(0, -5) + zwarakay + " ... ";
} else if (isUofDu && result.slice(-1) === " ") {
result = result.slice(0, -1) + zwarakey + " ";
result = result.slice(0, -1) + zwarakay + " ";
} else {
result += phonemeInfo.diacritic;
}
}
// TODO: The middle stuff might be unneccessary/unhelpful
const isACommaWithoutAyn = (phoneme === "'" && (p[pIndex] !== "ع" && !(isMiddle && p[pIndex] === "ئ")));
const isACommaWithoutAyn =
phoneme === "'" && p[pIndex] !== "ع" && !(isMiddle && p[pIndex] === "ئ");
// if the previous phoneme was a consonant insert a sukun
// console.log("Will I go into the adding thing?");
if (!isBeginning && previousPhonemeWasAConsonant && phonemeInfo.consonant && phonemes[i - 1] !== "'" && p[pIndex] !== "ع") {
if (
!isBeginning &&
previousPhonemeWasAConsonant &&
phonemeInfo.consonant &&
phonemes[i - 1] !== "'" &&
p[pIndex] !== "ع"
) {
result += isDoubleConsonant ? tashdeed : sukun;
}
if (isEnding && isDoubleConsonant) {
@ -417,30 +643,38 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
}
}
// if there's a pashto letter for the phoneme, insert it
if (!isEndingAynVowel && !isACommaWithoutAyn && (phonemeInfo.possibilities || isEnding)) {
if (
!isEndingAynVowel &&
!isACommaWithoutAyn &&
(phonemeInfo.possibilities || isEnding)
) {
// need the isSpace check to prevent weird behaviour with izafe
if (!isUofDu) {
if (isAnAEndingAfterHey) {
if (isAnAEndingAfterHay) {
result += zwar;
if (p[pIndex] === " ") {
result += " ";
}
} else {
result += (isDoubleConsonant || isSpace(p[pIndex])) ? "" : p[pIndex];
result += isDoubleConsonant || isSpace(p[pIndex]) ? "" : p[pIndex];
}
}
pIndex++;
}
if (isEnding) {
if (isUofDu) {
result += zwarakey;
result += zwarakay;
} else if (phonemeInfo.hamzaOnEnd) {
result += hamzaAbove;
} else if (phonemeInfo.takesSukunOnEnding) {
result += sukun;
} else if (p[pIndex] === daggerAlif) {
result += daggerAlif;
} else if (isEndSpace(p[pIndex]) && p[pIndex - 1] === "ه" && phonemeInfo.takesDiacriticBeforeGurdaHeyEnding) {
} else if (
isEndSpace(p[pIndex]) &&
p[pIndex - 1] === "ه" &&
phonemeInfo.takesDiacriticBeforeGurdaHayEnding
) {
result = result.slice(0, -1) + phonemeInfo.diacritic + "ه";
}
}
@ -456,13 +690,20 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
}
return;
}
previousPhonemeWasAConsonant = (!isEnding && phonemeInfo.consonant) ? true : false;
previousPhonemeWasAConsonant =
!isEnding && phonemeInfo.consonant ? true : false;
// ignore the ع or ئ if there's not a ' in the phonetics
const nextPhonemeInfo = phonemeTable.find((element) => phonemes[i + 1] === element.phoneme);
const nextPhonemeInfo = phonemeTable.find(
(element) => phonemes[i + 1] === element.phoneme
);
if (
["ع", "ئ"].includes(p[pIndex]) &&
![phonemes[i + 1], phonemes[i + 2]].includes("'") &&
!(nextPhonemeInfo && nextPhonemeInfo.diacritic && isEndSpace(p[pIndex + 1])) && // don't skip the ع on the end if there's another short letter coming after it
!(
nextPhonemeInfo &&
nextPhonemeInfo.diacritic &&
isEndSpace(p[pIndex + 1])
) && // don't skip the ع on the end if there's another short letter coming after it
!(p[pIndex] === "ئ" && isEndSpace(p[pIndex + 1])) && // don't skip ئ on the end
!phonemeInfo.isIzafe
) {
@ -476,7 +717,11 @@ export function phoneticsToDiacritics(ps: string, ph: string, forbidOoPrefixes:
return;
}
// if we've arrived at a space in the Pashto, move along before the next iteration
if (isSpace(p[pIndex]) && phonemes[i + 1] !== "-i-" && !upcomingAEndingAfterHey) {
if (
isSpace(p[pIndex]) &&
phonemes[i + 1] !== "-i-" &&
!upcomingAEndingAfterHay
) {
result += " ";
pIndex++;
}

2
src/lib/src/sandwiches.ts
View File

@ -107,7 +107,7 @@ export const sandwiches: T.Sandwich[] = [
{
type: "sandwich",
before: { p: "د", f: "du" },
after: { p: "په حیث", f: "pu heys" },
after: { p: "په حیث", f: "pu hays" },
e: "as",
},
{

17
src/lib/src/translate-phonetics-replacer.ts
View File

@ -105,14 +105,14 @@ export const replacerInfo: IReplacerInfoItem[] = [
ipa: "ɪ́",
},
{
char: "ey",
char: "ay",
alalc: "ay",
ipa: "ai",
ipa: "ay",
},
{
char: "éy",
char: "áy",
alalc: "áy",
ipa: "ái",
ipa: "áj",
},
{
char: "ee",
@ -140,9 +140,9 @@ export const replacerInfo: IReplacerInfoItem[] = [
ipa: "u:j",
},
{
char: "eyy",
alalc: "ạy",
ipa: "ɛ̝j",
char: "ey",
alalc: "ey",
ipa: "ej",
},
{
char: "e",
@ -351,4 +351,5 @@ export const replacerInfo: IReplacerInfoItem[] = [
];
// tslint:disable-next-line
export const replacerRegex = /aay|áay|aa|áa|a|á|U|Ú|u|ú|ooy|o{1,2}|óo|ó|ey|éy|e{1,2}|ée|é|uy|úy|i|í|w|y|q|g|ts|sh|s|dz|z|t|T|d|D|r|R|n|N|f|b|p|x|kh|q|k|gh|g|G|j|ch|l|l|m|h/g;
export const replacerRegex =
/aay|áay|aa|áa|a|á|U|Ú|u|ú|ooy|o{1,2}|óo|ó|ay|áy|e{1,2}|ée|é|ey|éy|uy|úy|i|í|w|y|q|g|ts|sh|s|dz|z|t|T|d|D|r|R|n|N|f|b|p|x|kh|q|k|gh|g|G|j|ch|l|l|m|h/g;

21
src/lib/src/translate-phonetics.test.ts
View File

@ -6,9 +6,7 @@
*
*/
import {
translatePhonetics,
} from "./translate-phonetics";
import { translatePhonetics } from "./translate-phonetics";
const dialects = ["southern", "standard", "peshawer"];
const systems = ["ipa", "alalc"];
@ -54,11 +52,11 @@ const translations = [
},
},
{
original: "saRey",
original: "saRay",
ipa: {
southern: "saɻai",
standard: "saɻai",
peshawer: "saɻai",
southern: "saɻaj",
standard: "saɻaj",
peshawer: "saɻaj",
},
alalc: {
southern: "saṛay",
@ -72,10 +70,8 @@ translations.forEach((t) => {
systems.forEach((system) => {
// check each dialect with given system
dialects.forEach((dialect) => {
test(
// @ts-ignore
`${t.original} should be translated to ${t.ipa[dialect]} using ${system} with ${dialect} dialect`,
() => {
test(// @ts-ignore
`${t.original} should be translated to ${t.ipa[dialect]} using ${system} with ${dialect} dialect`, () => {
const translated = translatePhonetics(t.original, {
// @ts-ignore
system,
@ -84,8 +80,7 @@ translations.forEach((t) => {
});
// @ts-ignore
expect(translated).toBe(t[system][dialect]);
},
);
});
});
});
});

293
src/lib/src/validate-entry.test.ts
View File

@ -8,16 +8,21 @@
import { standardizeEntry, validateEntry } from "./validate-entry";
import * as T from "../../types";
import { standardizePhonetics } from "./standardize-pashto";
const toTest: {
input: any,
output: T.DictionaryEntryError | { ok: true } | { checkComplement: true },
input: any;
output: T.DictionaryEntryError | { ok: true } | { checkComplement: true };
}[] = [
{
input: { ts: undefined },
output: {
errors: ["missing ts", "missing i", "missing p", "missing f", "missing e"],
errors: [
"missing ts",
"missing i",
"missing p",
"missing f",
"missing e",
],
p: "",
f: "",
e: "",
@ -37,7 +42,14 @@ const toTest: {
},
},
{
input: {"i":293,"ts":1527821299,"p":"اخطار","f":"ixtáar","e":"warning, reprimand, admonishment","c":"n. m."},
input: {
i: 293,
ts: 1527821299,
p: "اخطار",
f: "ixtáar",
e: "warning, reprimand, admonishment",
c: "n. m.",
},
output: {
errors: ["script and phonetics do not match for p and f"],
p: "اخطار",
@ -48,7 +60,17 @@ const toTest: {
},
},
{
input: {"i":2433,"ts":1527815197,"p":"پښتون","f":"puxtoon","e":"Pashtun","c":"n. m. unisex / adj. irreg.","infap":"پښتانه","infaf":"puxtaanu","infbf":"puxtan"},
input: {
i: 2433,
ts: 1527815197,
p: "پښتون",
f: "puxtoon",
e: "Pashtun",
c: "n. m. unisex / adj. irreg.",
infap: "پښتانه",
infaf: "puxtaanu",
infbf: "puxtan",
},
output: {
errors: ["missing infbp"],
p: "پښتون",
@ -59,7 +81,17 @@ const toTest: {
},
},
{
input: {"i":2433,"ts":1527815197,"p":"پښتون","f":"puxtoon","e":"Pashtun","c":"n. m. unisex / adj. irreg.","infap":"پښتانه","infaf":"puxtaanu","infbp":"پښتن"},
input: {
i: 2433,
ts: 1527815197,
p: "پښتون",
f: "puxtoon",
e: "Pashtun",
c: "n. m. unisex / adj. irreg.",
infap: "پښتانه",
infaf: "puxtaanu",
infbp: "پښتن",
},
output: {
errors: ["missing infbf"],
p: "پښتون",
@ -70,9 +102,22 @@ const toTest: {
},
},
{
input: {"i":2433,"ts":1527815197,"p":"پښتون","f":"puxtoon","e":"Pashtun","c":"n. m. unisex / adj. irreg.","infap":"پښتانه","infaf":"puktaanu","infbp":"پښتن"},
input: {
i: 2433,
ts: 1527815197,
p: "پښتون",
f: "puxtoon",
e: "Pashtun",
c: "n. m. unisex / adj. irreg.",
infap: "پښتانه",
infaf: "puktaanu",
infbp: "پښتن",
},
output: {
errors: ["script and phonetics do not match for infap and infaf", "missing infbf"],
errors: [
"script and phonetics do not match for infap and infaf",
"missing infbf",
],
p: "پښتون",
f: "puxtoon",
e: "Pashtun",
@ -81,7 +126,19 @@ const toTest: {
},
},
{
input: {"i":5000,"ts":1527819674,"p":"څملاستل","f":"tsumlaastúl","e":"to lie down","l":1596485996977,"separationAtP":2,"c":"v. intrans. seperable","psp":"څمل","psf":"tsaml","noOo":true},
input: {
i: 5000,
ts: 1527819674,
p: "څملاستل",
f: "tsumlaastúl",
e: "to lie down",
l: 1596485996977,
separationAtP: 2,
c: "v. intrans. seperable",
psp: "څمل",
psf: "tsaml",
noOo: true,
},
output: {
errors: ["missing separationAtF"],
p: "څملاستل",
@ -92,9 +149,24 @@ const toTest: {
},
},
{
input: {"i":5000,"ts":1527819674,"p":"څملاستل","f":"sumlaastúl","e":"to lie down","l":1596485996977,"separationAtP":2,"c":"v. intrans. seperable","psp":"څمل","psf":"tsaml","noOo":true},
input: {
i: 5000,
ts: 1527819674,
p: "څملاستل",
f: "sumlaastúl",
e: "to lie down",
l: 1596485996977,
separationAtP: 2,
c: "v. intrans. seperable",
psp: "څمل",
psf: "tsaml",
noOo: true,
},
output: {
errors: ["script and phonetics do not match for p and f", "missing separationAtF"],
errors: [
"script and phonetics do not match for p and f",
"missing separationAtF",
],
p: "څملاستل",
f: "sumlaastúl",
e: "to lie down",
@ -103,7 +175,19 @@ const toTest: {
},
},
{
input: {"i":5000,"ts":1527819674,"p":"څملاستل","f":"tsumlaastúl","e":"to lie down","l":1596485996977,"separationAtF":4,"c":"v. intrans. seperable","psp":"څمل","psf":"tsaml","noOo":true},
input: {
i: 5000,
ts: 1527819674,
p: "څملاستل",
f: "tsumlaastúl",
e: "to lie down",
l: 1596485996977,
separationAtF: 4,
c: "v. intrans. seperable",
psp: "څمل",
psf: "tsaml",
noOo: true,
},
output: {
errors: ["missing separationAtP"],
p: "څملاستل",
@ -114,7 +198,14 @@ const toTest: {
},
},
{
input: {"i":2222,"ts":1571859113828,"p":"پخول","f":"pakhawul","e":"to cook, prepare, to cause to ripen, mature","c":"v. stat. comp. trans."},
input: {
i: 2222,
ts: 1571859113828,
p: "پخول",
f: "pakhawul",
e: "to cook, prepare, to cause to ripen, mature",
c: "v. stat. comp. trans.",
},
output: {
errors: ["missing complement for compound verb"],
p: "پخول",
@ -125,21 +216,50 @@ const toTest: {
},
},
{
input: {"i":2222,"ts":1571859113828,"p":"پخول","f":"pakhawul","e":"to cook, prepare, to cause to ripen, mature","l":1574867531681,"c":"v. stat. comp. trans."},
input: {
i: 2222,
ts: 1571859113828,
p: "پخول",
f: "pakhawul",
e: "to cook, prepare, to cause to ripen, mature",
l: 1574867531681,
c: "v. stat. comp. trans.",
},
output: {
checkComplement: true,
},
},
{
input: {"i":2231,"ts":1527812013,"p":"پراخ","f":"praakh, paráakh","e":"wide, broad, spacious, vast","c":"adj."},
input: {
i: 2231,
ts: 1527812013,
p: "پراخ",
f: "praakh, paráakh",
e: "wide, broad, spacious, vast",
c: "adj.",
},
output: { ok: true },
},
{
input: {"i":0,"ts":1527812013,"p":"پراخ","f":"praakh, paráakh","e":"wide, broad, spacious, vast","c":"adj."},
input: {
i: 0,
ts: 1527812013,
p: "پراخ",
f: "praakh, paráakh",
e: "wide, broad, spacious, vast",
c: "adj.",
},
output: { ok: true },
},
{
input: {"i":12,"ts":1575058859661,"p":"آبدار","f":"aawdáar","e":"watery, damp, humid, juicy","c":"adj."},
input: {
i: 12,
ts: 1575058859661,
p: "آبدار",
f: "aawdáar",
e: "watery, damp, humid, juicy",
c: "adj.",
},
output: {
errors: ["script and phonetics do not match for p and f"],
p: "آبدار",
@ -150,37 +270,84 @@ const toTest: {
},
},
{
input: {"ts":1591033069786,"i":7717,"p":"ستړی کول","f":"stuRey kawul","g":"stuReykedul","e":"to get tired, fatigued","c":"v. stat. comp. intrans.","l":1527815306,"ec":"get","ep":"tired"},
input: {
ts: 1591033069786,
i: 7717,
p: "ستړی کول",
f: "stuRay kawul",
g: "stuRaykedul",
e: "to get tired, fatigued",
c: "v. stat. comp. intrans.",
l: 1527815306,
ec: "get",
ep: "tired",
},
output: {
errors: ["wrong ending for intrans. stat. comp"],
p: "ستړی کول",
f: "stuRey kawul",
f: "stuRay kawul",
e: "to get tired, fatigued",
ts: 1591033069786,
erroneousFields: ["p", "f"],
},
},
{
input: {"ts":1591033078746,"i":7716,"p":"ستړی کېدل","f":"stuRey kedul","g":"stuReykawul","e":"to make tired, wear out","c":"v. stat. comp. trans.","l":1527815306,"ec":"make","ep":"tired"},
input: {
ts: 1591033078746,
i: 7716,
p: "ستړی کېدل",
f: "stuRay kedul",
g: "stuRaykawul",
e: "to make tired, wear out",
c: "v. stat. comp. trans.",
l: 1527815306,
ec: "make",
ep: "tired",
},
output: {
errors: ["wrong ending for trans. stat. comp"],
p: "ستړی کېدل",
f: "stuRey kedul",
f: "stuRay kedul",
e: "to make tired, wear out",
ts: 1591033078746,
erroneousFields: ["p", "f"],
},
},
{
input: {"i":12,"ts":1575058859661,"p":"آبدار","f":"aawdáar","e":"watery, damp, humid, juicy","c":"adj.","diacExcept":true},
input: {
i: 12,
ts: 1575058859661,
p: "آبدار",
f: "aawdáar",
e: "watery, damp, humid, juicy",
c: "adj.",
diacExcept: true,
},
output: { ok: true },
},
{
input: {"i":12,"ts":1575058859661,"p":"آبدار","f":"aawdáar","e":"watery, damp, humid, juicy","c":"adj.","diacExcept":true},
input: {
i: 12,
ts: 1575058859661,
p: "آبدار",
f: "aawdáar",
e: "watery, damp, humid, juicy",
c: "adj.",
diacExcept: true,
},
output: { ok: true },
},
{
input: {"ts":1527812488,"i":1934,"p":"بې چاره","f":"bechaara","g":"bechaara","e":"poor thing, pitiful","r":3,"c":"adj."},
input: {
ts: 1527812488,
i: 1934,
p: "بې چاره",
f: "bechaara",
g: "bechaara",
e: "poor thing, pitiful",
r: 3,
c: "adj.",
},
output: {
errors: ["spacing discrepency between p and f"],
p: "بې چاره",
@ -191,7 +358,16 @@ const toTest: {
},
},
{
input: {"ts":1527812488,"i":1934,"p":"بېچاره","f":"be chaara","g":"bechaara","e":"poor thing, pitiful","r":3,"c":"adj."},
input: {
ts: 1527812488,
i: 1934,
p: "بېچاره",
f: "be chaara",
g: "bechaara",
e: "poor thing, pitiful",
r: 3,
c: "adj.",
},
output: {
errors: ["spacing discrepency between p and f"],
p: "بېچاره",
@ -202,11 +378,31 @@ const toTest: {
},
},
{
input: {"ts":1527812488,"i":1934,"p":"بې چاره","f":"be chaara","g":"bechaara","e":"poor thing, pitiful","r":3,"c":"adj."},
output: { ok: true }
input: {
ts: 1527812488,
i: 1934,
p: "بې چاره",
f: "be chaara",
g: "bechaara",
e: "poor thing, pitiful",
r: 3,
c: "adj.",
},
output: { ok: true },
},
{
input: {"ts":1527814265,"i":12969,"p":"مکتب","f":"maktab","g":"maktab","e":"school","r":4,"c":"n. m.","app":"مکاتب","apf":"ma kaatib"},
input: {
ts: 1527814265,
i: 12969,
p: "مکتب",
f: "maktab",
g: "maktab",
e: "school",
r: 4,
c: "n. m.",
app: "مکاتب",
apf: "ma kaatib",
},
output: {
errors: ["spacing discrepency between app and apf"],
p: "مکتب",
@ -217,9 +413,23 @@ const toTest: {
},
},
{
input: {"ts":1527815870,"i":183,"p":"اثر","f":"asar","g":"asar","e":"influence, impression, tracks, affect","r":4,"c":"n. m.","app":"اثرات, آثار","apf":"asráat"},
input: {
ts: 1527815870,
i: 183,
p: "اثر",
f: "asar",
g: "asar",
e: "influence, impression, tracks, affect",
r: 4,
c: "n. m.",
app: "اثرات, آثار",
apf: "asráat",
},
output: {
errors: ["difference in variation length between app and apf", "script and phonetics do not match for app and apf"],
errors: [
"difference in variation length between app and apf",
"script and phonetics do not match for app and apf",
],
p: "اثر",
f: "asar",
e: "influence, impression, tracks, affect",
@ -236,6 +446,23 @@ test("validateEntry should work", () => {
});
test("standardizeEntry", () => {
expect(standardizeEntry({"i":195,"ts":1527822036,"p":"اجتماعي","f":"ijtimaa‘ee, ijtimaayee","g":"ijtimaaee,ijtimaayee","e":"public, social, societal","c":"adj."}))
.toEqual({"i":195,"ts":1527822036,"p":"اجتماعي","f":"ijtimaa'ee, ijtimaayee","g":"ijtimaaee,ijtimaayee","e":"public, social, societal","c":"adj."});
expect(
standardizeEntry({
i: 195,
ts: 1527822036,
p: "اجتماعي",
f: "ijtimaa‘ee, ijtimaayee",
g: "ijtimaaee,ijtimaayee",
e: "public, social, societal",
c: "adj.",
})
).toEqual({
i: 195,
ts: 1527822036,
p: "اجتماعي",
f: "ijtimaa'ee, ijtimaayee",
g: "ijtimaaee,ijtimaayee",
e: "public, social, societal",
c: "adj.",
});
});