Refuse a body the PDU's own data_coding cannot carry (#98)

* Regression tests for a body the PDU's own data_coding cannot carry

* Refuse a body the PDU's own data_coding cannot carry, in the codec both send paths build through

* Record the codec's body refusal, and drop two todo entries it and the interop run close

* Regression tests for the aliased body TLV and the data_coding short_message settles

* Find the body TLV by tag id, leave data_coding to the field that will be read, and correct the record

* Record the two architecture findings this change does not close

* Regression tests for a duplicated body tag and a short_message the wire never carries

* Resolve every body TLV against the field that will be read, and move TLV writing to its table

* Regression tests for a body only the TLV carries and an empty short_message

* Let only octets the command writes settle the alphabet, and stop shadowing the TLV table
This commit is contained in:
2026-09-09 19:33:36 +02:00
committed by GitHub
parent c06cc0648b
commit ef13290230
9 changed files with 476 additions and 102 deletions
+7
View File
@@ -123,6 +123,13 @@ export function detect(value: string): EncodingName {
export type Unencodable = { char: string; index: number };
/** What an alphabet could not carry, said the one way: the character, its code point and its index. */
export function unencodableText(at: Unencodable): string {
const point = (at.char.codePointAt(0) ?? 0).toString(16).toUpperCase().padStart(4, '0');
return `${JSON.stringify(at.char)} (U+${point}) at index ${String(at.index)}`;
}
/** The first character `encoding` cannot carry, or undefined where it carries every one of them. */
export function unencodable(message: string, encoding: EncodingName): Unencodable | undefined {
const codec = encodings[encoding];
+58
View File
@@ -1,4 +1,5 @@
import type { ParamValue, WireType } from './types.ts';
import type { Result } from '../result.ts';
import { tlv } from './types.ts';
export type TlvDefinition = {
@@ -104,3 +105,60 @@ export type Tlv = {
tagName: string | undefined;
tagValue: ParamValue;
};
export type TlvInput = {
/** Resolved from the record key; pass it for a tag the TLV table does not define. */
tagId?: number | undefined;
tagValue: ParamValue;
};
export function tagIdOf(name: string, input: TlvInput): Result<{ tagId: number }> {
const tagId = input.tagId ?? tlvs[name]?.id;
if (tagId === undefined) {
return { err: new Error(`TLV "${name}": unknown tag name, give it a tagId`) };
}
if (!Number.isInteger(tagId) || tagId < 0 || tagId > 0xFFFF) {
return { err: new Error(`TLV "${name}": tagId ${String(tagId)} out of range 0-65535`) };
}
return { tagId };
}
/** Each TLV as its four octet header and the value the tag's own wire type writes. */
export function writeTlvs(inputs: Record<string, TlvInput> | undefined): Result<{ chunks: Buffer[] }> {
const chunks: Buffer[] = [];
for (const [name, input] of Object.entries(inputs ?? {})) {
const tag = tagIdOf(name, input);
if (tag.err) return { err: tag.err };
const type = tlvsById[tag.tagId]?.type ?? tlvDefault;
const sized = type.size(input.tagValue);
if (sized.err) {
return { err: new Error(`TLV "${name}": ${sized.err.message}`) };
}
if (sized.size > 0xffff) {
return { err: new Error(`TLV "${name}": ${String(sized.size)} octets overflow the two octet length`) };
}
const chunk = Buffer.alloc(sized.size + 4);
chunk.writeUInt16BE(tag.tagId, 0);
chunk.writeUInt16BE(sized.size, 2);
const written = type.write(input.tagValue, chunk, 4);
if (written.err) {
return { err: new Error(`TLV "${name}": ${written.err.message}`) };
}
chunks.push(chunk);
}
return { chunks };
}
+21 -2
View File
@@ -1,7 +1,7 @@
import type { Result } from './result.ts';
import type { EncodingName } from './defs/encodings.ts';
import { detect, encodingByDataCoding, encodings } from './defs/encodings.ts';
import { hasUdh } from './defs/constants.ts';
import { detect, encodingByDataCoding, encodings, unencodable, unencodableText } from './defs/encodings.ts';
import { consts, hasUdh } from './defs/constants.ts';
import { udhLength } from './udh.ts';
/** A single SMS carries 1120 bits, whatever the alphabet. */
@@ -27,6 +27,25 @@ export function encodeMessage(
return { buffer: encodings[resolved].encode(message), encoding: resolved };
}
/** A message body as octets, under the alphabet `dataCoding` resolves to, or one detected for it. */
export function encodeBody(
text: string,
dataCoding: number | undefined,
): Result<{ buffer: Buffer; dataCoding: number }> {
if (dataCoding === undefined) {
const detected = encodeMessage(text);
return { buffer: detected.buffer, dataCoding: consts.ENCODING[detected.encoding] };
}
const encoding = encodingByDataCoding(dataCoding);
const lost = unencodable(text, encoding);
return lost
? { err: new Error(`data_coding ${String(dataCoding)} resolves to ${encoding}, which cannot carry ${unencodableText(lost)}; pass a Buffer of octets, or a data_coding whose alphabet carries them`) }
: { buffer: encodings[encoding].encode(text), dataCoding };
}
export function decodeMessage(
buffer: Buffer,
dataCoding: number,
+96 -79
View File
@@ -3,15 +3,14 @@ import type { ErrorName } from './defs/errors.ts';
import type { ParamValue } from './defs/types.ts';
import type { PduHeader } from './pdu-refusal.ts';
import type { Result, VoidResult } from './result.ts';
import type { Tlv } from './defs/tlvs.ts';
import type { Tlv, TlvInput } from './defs/tlvs.ts';
import { PduRefusedError, framingRefusal } from './pdu-refusal.ts';
import { cmds, commandNameById, respNameFor } from './defs/commands.ts';
import { consts, hasUdh } from './defs/constants.ts';
import { decodeMessage, encodeMessage } from './message.ts';
import { detect, encodingByDataCoding } from './defs/encodings.ts';
import { hasUdh } from './defs/constants.ts';
import { decodeMessage, encodeBody } from './message.ts';
import { errorNameById, errors, isErrorName } from './defs/errors.ts';
import { paramNumber } from './defs/types.ts';
import { tlvDefault, tlvs, tlvsById } from './defs/tlvs.ts';
import { tagIdOf, tlvDefault, tlvs, tlvsById, writeTlvs } from './defs/tlvs.ts';
/** The highest sequence number this library hands out; SMPP 3.4 4.7.1 reserves 0x7fffffff. */
export const maxSeqNr = 2147483646;
@@ -19,12 +18,6 @@ export const maxSeqNr = 2147483646;
/** What the field holds. Read and echoed in full, because peers do write above the spec's range. */
const maxWireSeqNr = 0xFFFFFFFF;
export type TlvInput = {
/** Resolved from the record key; pass it for a tag the TLV table does not define. */
tagId?: number | undefined;
tagValue: ParamValue;
};
export type PduObjectInput<C extends CommandName = CommandName> = {
cmdName: C;
cmdStatus?: ErrorName;
@@ -53,6 +46,8 @@ export type PduObject = {
tlvs: Record<string, Tlv>;
};
export type { TlvInput };
const respBit = 0x80000000;
export function isResp(pduObj: Pick<PduObject, 'cmdId'>): boolean {
@@ -71,44 +66,98 @@ export function isCommand<C extends CommandName>(
return pduObj.cmdName === cmdName;
}
function tagIdOf(name: string, input: TlvInput): Result<{ tagId: number }> {
const tagId = input.tagId ?? tlvs[name]?.id;
type ResolvedBody = {
params: Record<string, ParamValue | undefined>;
tlvs: Record<string, TlvInput> | undefined;
};
if (tagId === undefined) {
return { err: new Error(`TLV "${name}": unknown tag name, give it a tagId`) };
}
if (!Number.isInteger(tagId) || tagId < 0 || tagId > 0xFFFF) {
return { err: new Error(`TLV "${name}": tagId ${String(tagId)} out of range 0-65535`) };
}
return { tagId };
function codingOf(params: Record<string, ParamValue | undefined>): number | undefined {
return typeof params.data_coding === 'number' ? params.data_coding : undefined;
}
/** Encoding a string short_message settles data_coding and sm_length; a buffer settles sm_length. */
function resolveShortMessage(
params: Record<string, ParamValue | undefined>,
): Record<string, ParamValue | undefined> {
const message = params.short_message;
type CarriedBody = { name: string; text: string; tlv: TlvInput };
if (Buffer.isBuffer(message)) {
return params.sm_length === undefined
? { ...params, sm_length: message.length }
: { ...params };
/** Every entry carrying body text, under whatever names their tagIds are keyed to. */
function carriedBodies(input: Record<string, TlvInput> | undefined): CarriedBody[] {
const carried: CarriedBody[] = [];
for (const [name, tlv] of Object.entries(input ?? {})) {
const tag = tagIdOf(name, tlv);
if (!tag.err && tag.tagId === tlvs.message_payload.id && typeof tlv.tagValue === 'string') {
carried.push({ name, text: tlv.tagValue, tlv });
}
}
if (typeof message !== 'string') return { ...params };
return carried;
}
const dataCoding = params.data_coding;
const encoding = typeof dataCoding === 'number' ? encodingByDataCoding(dataCoding) : detect(message);
const encoded = encodeMessage(message, encoding);
/** messageOctets() reads short_message wherever it holds an octet, and the TLV only where it does not. */
function carriesOctets(value: ParamValue | undefined): boolean {
return Buffer.isBuffer(value) && value.length > 0;
}
return {
...params,
data_coding: typeof dataCoding === 'number' ? dataCoding : consts.ENCODING[encoded.encoding],
short_message: encoded.buffer,
sm_length: encoded.buffer.length,
};
/** The short_message the command's own table will write, since writeParams() ignores any other. */
function writtenBody(definition: CommandDefinition, value: ParamValue | undefined): ParamValue | undefined {
return definition.params?.short_message === undefined ? undefined : value;
}
/** Encoded in place, settling data_coding where `settles` says no mandatory field will carry it. */
function resolveCarried(
resolved: ResolvedBody,
inputs: Record<string, TlvInput> | undefined,
dataCoding: number | undefined,
settles: boolean,
): VoidResult {
for (const carried of carriedBodies(inputs)) {
const encoded = encodeBody(carried.text, dataCoding);
if (encoded.err) return { err: new Error(`TLV "${carried.name}": ${encoded.err.message}`) };
if (settles) resolved.params.data_coding = encoded.dataCoding;
resolved.tlvs = { ...resolved.tlvs, [carried.name]: { ...carried.tlv, tagValue: encoded.buffer } };
}
return {};
}
/** data_coding names the alphabet of the body, and short_message settles it where it carries octets. */
function resolveBody(
params: Record<string, ParamValue | undefined>,
tlvs: Record<string, TlvInput> | undefined,
definition: CommandDefinition,
): Result<ResolvedBody> {
const message = writtenBody(definition, params.short_message);
const resolved: ResolvedBody = { params: { ...params }, tlvs };
if (Buffer.isBuffer(message) && params.sm_length === undefined) {
resolved.params.sm_length = message.length;
}
if (typeof message === 'string') {
const encoded = encodeBody(message, codingOf(params));
if (encoded.err) {
return { err: new Error(`Parameter "short_message" of "${definition.command}": ${encoded.err.message}`) };
}
if (carriesOctets(encoded.buffer)) resolved.params.data_coding = encoded.dataCoding;
resolved.params.short_message = encoded.buffer;
resolved.params.sm_length = encoded.buffer.length;
}
// Only octets the command's own table will write can settle the alphabet the PDU declares.
const settles = !carriesOctets(writtenBody(definition, resolved.params.short_message));
const carried = resolveCarried(
resolved,
tlvs,
settles ? codingOf(params) : codingOf(resolved.params),
settles,
);
return carried.err ? { err: carried.err } : resolved;
}
function writeParams(
@@ -139,42 +188,6 @@ function writeParams(
return { chunks };
}
function writeTlvs(tlvs: Record<string, TlvInput> | undefined): Result<{ chunks: Buffer[] }> {
const chunks: Buffer[] = [];
for (const [name, tlv] of Object.entries(tlvs ?? {})) {
const tag = tagIdOf(name, tlv);
if (tag.err) return { err: tag.err };
const type = tlvsById[tag.tagId]?.type ?? tlvDefault;
const sized = type.size(tlv.tagValue);
if (sized.err) {
return { err: new Error(`TLV "${name}": ${sized.err.message}`) };
}
if (sized.size > 0xffff) {
return { err: new Error(`TLV "${name}": ${String(sized.size)} octets overflow the two octet length`) };
}
const chunk = Buffer.alloc(sized.size + 4);
chunk.writeUInt16BE(tag.tagId, 0);
chunk.writeUInt16BE(sized.size, 2);
const written = type.write(tlv.tagValue, chunk, 4);
if (written.err) {
return { err: new Error(`TLV "${name}": ${written.err.message}`) };
}
chunks.push(chunk);
}
return { chunks };
}
/**
* SMPP 3.4: a response reporting a failure carries no body, so its fields are not "unused but
* present" — they are absent, and a peer that reads them anyway reads past the end of the PDU.
@@ -188,11 +201,15 @@ function buildBody(
): Result<{ body: Buffer }> {
if (errors[cmdStatus] !== 0 && definition.id >= respBit) return { body: Buffer.alloc(0) };
const written = writeParams(definition, resolveShortMessage(params), cmdName);
const body = resolveBody(params, tlvs, definition);
if (body.err) return { err: body.err };
const written = writeParams(definition, body.params, cmdName);
if (written.err) return { err: written.err };
const writtenTlvs = writeTlvs(tlvs);
const writtenTlvs = writeTlvs(body.tlvs);
if (writtenTlvs.err) return { err: writtenTlvs.err };
+2 -4
View File
@@ -7,7 +7,7 @@ import type { SmppLog } from './log.ts';
import type { SmsIdNotation } from './sms-id.ts';
import { UnansweredError } from './unanswered-error.ts';
import { consts, defaultMessagingMode, isMessagingMode, isSubmitMessagingMode, submitMessagingModes } from './defs/constants.ts';
import { detect, encodingNames, isEncodingName, unencodable } from './defs/encodings.ts';
import { detect, encodingNames, isEncodingName, unencodable, unencodableText } from './defs/encodings.ts';
import { namedValue } from './error-from.ts';
import { normaliseSmsId } from './sms-id.ts';
import { paramText } from './defs/types.ts';
@@ -168,9 +168,7 @@ function refusedEncoding(encoding: unknown): Error {
}
function refusedText(encoding: EncodingName, at: Unencodable): Error {
const point = (at.char.codePointAt(0) ?? 0).toString(16).toUpperCase().padStart(4, '0');
return new Error(`encoding ${encoding} cannot carry ${JSON.stringify(at.char)} (U+${point}) at index ${String(at.index)}; name UCS2 or leave encoding out`);
return new Error(`encoding ${encoding} cannot carry ${unencodableText(at)}; name UCS2 or leave encoding out`);
}
/** An alphabet the caller named has to carry the message; the one detect() picks always does. */