@laisuk/opencc-fmmseg-wasm 0.3.9 → 0.4.0

package/README.md

@@ -12,25 +12,25 @@ This package provides high-quality Simplified Chinese ↔ Traditional Chinese co
 
 Features:
 
-* OpenCC-compatible conversion configs
-* Pure WebAssembly (no native binaries)
-* Browser-friendly
-* TypeScript-friendly APIs
-* Fast Rust backend
-* FMM-based phrase segmentation
-* Traditional Chinese regional variants
-* Japanese Shinjitai conversion support
-* Chinese script detection (`zho_check`)
-* Optional CJK Compatibility Ideograph normalization
-* In-memory Office / EPUB document conversion
-* Zero-dependency Node.js CLI
+- OpenCC-compatible conversion configs
+- Pure WebAssembly (no native binaries)
+- Browser-friendly
+- TypeScript-friendly APIs
+- Fast Rust backend
+- FMM-based phrase segmentation
+- Traditional Chinese regional variants
+- Japanese Shinjitai conversion support
+- Chinese script detection (`zho_check`)
+- Optional CJK Compatibility Ideograph normalization
+- In-memory Office / EPUB document conversion
+- Zero-dependency Node.js CLI
 
 Package profile:
 
-* 0 runtime dependencies
-* 1 WASM file
-* 18 conversion configs
-* 100% offline
+- 0 runtime dependencies
+- 1 WASM file
+- 20 conversion configs
+- 100% offline
 
 ---
 
@@ -52,10 +52,10 @@ import init, {
 
 await init();
 
-const cc = new OpenccWasm("s2t");
+const cc = new OpenccWasm("t2s");
 
-console.log(cc.convert("汉字", false));
-// 漢字
+console.log(cc.convert("漢字", false));
+// 汉字
 
 console.log(cc.convertDetofu("儼驂騑於上路", false, DetofuLevelWasm.ExtB));
 // 俨骖騑于上路
@@ -63,56 +63,6 @@ console.log(cc.convertDetofu("儼驂騑於上路", false, DetofuLevelWasm.ExtB))
 
 ---
 
-## Using Config Enums
-
-```javascript
-import init, {
-    OpenccWasm,
-    OpenccConfigWasm
-} from "@laisuk/opencc-fmmseg-wasm";
-
-await init();
-
-const cc = OpenccWasm.newWithEnum(
-    OpenccConfigWasm.S2hkp
-);
-
-console.log(cc.convert("别随便录影侵犯个人隐私权", false));
-// 別隨便錄影侵犯個人私隱權
-```
-
----
-
-## Supported Configs
-
-| Config  | Enum                     | Description                                           |
-|---------|--------------------------|-------------------------------------------------------|
-| `s2t`   | `OpenccConfigWasm.S2t`   | Simplified Chinese → Traditional Chinese              |
-| `s2tw`  | `OpenccConfigWasm.S2tw`  | Simplified Chinese → Taiwan Traditional               |
-| `s2twp` | `OpenccConfigWasm.S2twp` | Simplified Chinese → Taiwan Traditional (phrases)     |
-| `s2hk`  | `OpenccConfigWasm.S2hk`  | Simplified Chinese → Hong Kong Traditional            |
-| `s2hkp` | `OpenccConfigWasm.S2hkp` | Simplified Chinese → Hong Kong Traditional (phrases)  |
-| `t2s`   | `OpenccConfigWasm.T2s`   | Traditional Chinese → Simplified Chinese              |
-| `t2tw`  | `OpenccConfigWasm.T2tw`  | Traditional Chinese → Taiwan Traditional              |
-| `t2twp` | `OpenccConfigWasm.T2twp` | Traditional Chinese → Taiwan Traditional (phrases)    |
-| `t2hk`  | `OpenccConfigWasm.T2hk`  | Traditional Chinese → Hong Kong Traditional           |
-| `t2hkp` | `OpenccConfigWasm.T2hkp` | Traditional Chinese → Hong Kong Traditional (phrases) |
-| `tw2s`  | `OpenccConfigWasm.Tw2s`  | Taiwan Traditional → Simplified Chinese               |
-| `tw2sp` | `OpenccConfigWasm.Tw2sp` | Taiwan Traditional → Simplified Chinese (phrases)     |
-| `tw2t`  | `OpenccConfigWasm.Tw2t`  | Taiwan Traditional → Traditional Chinese              |
-| `tw2tp` | `OpenccConfigWasm.Tw2tp` | Taiwan Traditional → Traditional Chinese (phrases)    |
-| `hk2s`  | `OpenccConfigWasm.Hk2s`  | Hong Kong Traditional → Simplified Chinese            |
-| `hk2sp` | `OpenccConfigWasm.Hk2sp` | Hong Kong Traditional → Simplified Chinese (phrases)  |
-| `hk2t`  | `OpenccConfigWasm.Hk2t`  | Hong Kong Traditional → Traditional Chinese           |
-| `hk2tp` | `OpenccConfigWasm.Hk2tp` | Hong Kong Traditional → Traditional Chinese (phrases) |
-| `jp2t`  | `OpenccConfigWasm.Jp2t`  | Japanese Shinjitai → Traditional Chinese              |
-| `t2jp`  | `OpenccConfigWasm.T2jp`  | Traditional Chinese → Japanese Shinjitai              |
-
-The numeric enum values match the vendored Rust backend. Existing values are unchanged; `S2hkp = 17`, `Hk2sp = 18`,
-`T2hkp = 19`, and `Hk2tp = 20`.
-
----
-
 ## API
 
 ### Constructor
@@ -123,8 +73,8 @@ const cc = new OpenccWasm("s2t");
 
 Parameters:
 
-* `config` (optional): OpenCC config string
-* default: `"s2t"`
+- `config` (optional): OpenCC config string
+- default: `"s2t"`
 
 Example:
 
@@ -151,12 +101,12 @@ cc.convert(text, punctuation)
 
 Parameters:
 
-* `text`: input string
-* `punctuation`: whether to convert punctuation variants
+- `text`: input string
+- `punctuation`: whether to convert punctuation variants
 
 Returns:
 
-* converted string
+- converted string
 
 Example:
 
@@ -166,6 +116,85 @@ cc.convert("汉字", false);
 
 ---
 
+### setConfig
+
+```javascript
+cc.setConfig("t2s");
+```
+
+Returns:
+
+- `true` if valid
+- `false` if invalid
+
+---
+
+### getConfig
+
+```javascript
+cc.getConfig();
+```
+
+Returns current config string.
+
+---
+
+### isValidConfig
+
+```javascript
+OpenccWasm.isValidConfig("s2t");
+```
+
+---
+
+### getSupportedConfigs
+
+```javascript
+OpenccWasm.getSupportedConfigs();
+```
+
+Returns all supported config strings.
+
+Includes `s2hkp`, `hk2sp`, `t2hkp`, and `hk2tp`.
+
+---
+
+### getAvailableSlots
+
+```javascript
+const slots = OpenccWasm.getAvailableSlots();
+```
+
+Returns all canonical dictionary slot names accepted by `newWithCustomDicts` as a string array. The list is sourced from
+the core `DictSlot` definitions, so callers can use it to populate selectors or validate custom dictionary input without
+maintaining their own slot list.
+
+```javascript
+if (!OpenccWasm.getAvailableSlots().includes(slot)) {
+    throw new Error(`Unsupported dictionary slot: ${slot}`);
+}
+```
+
+---
+
+### zhoCheck
+
+Detect Chinese script type.
+
+```javascript
+cc.zhoCheck(text);
+```
+
+Returns:
+
+| Value | Meaning             |
+|-------|---------------------|
+| `0`   | Unknown / mixed     |
+| `1`   | Traditional Chinese |
+| `2`   | Simplified Chinese  |
+
+---
+
 ### normalizeCompat
 
 Normalize Unicode CJK Compatibility Ideographs before conversion.
@@ -176,11 +205,11 @@ cc.normalizeCompat(text)
 
 Parameters:
 
-* `text`: input string
+- `text`: input string
 
 Returns:
 
-* normalized string
+- normalized string
 
 Example:
 
@@ -197,9 +226,89 @@ console.log(cc.convert(normalized, false));
 // 天龙八部书里的乔峰是契丹人
 ```
 
-This is an optional pre-conversion pass for text that contains compatibility ideographs from Unicode compatibility
-ranges. Unmapped characters are preserved unchanged. Normal OpenCC conversion does not automatically run this pass, so
-call it explicitly when compatibility normalization is desired.
+This is an optional pre-conversion pass for text that contains CJK Compatibility Ideographs. Unmapped characters are
+preserved unchanged. Normal OpenCC conversion does not automatically run this pass, so call it explicitly when
+compatibility normalization is desired.
+
+### normalizeUnicodeCompat
+
+Normalize additional Unicode compatibility forms, CJK radicals, allographs, legacy glyphs, and selected
+compatibility-like punctuation before conversion.
+
+```javascript
+cc.normalizeUnicodeCompat(text)
+```
+
+Parameters:
+
+- `text`: input string
+
+Returns:
+
+- normalized string
+
+Example:
+
+```javascript
+const cc = new OpenccWasm("t2s");
+
+const input = "聼聼竒羙⽟䂖甁噐⾳";
+const normalized = cc.normalizeUnicodeCompat(input);
+
+console.log(normalized);
+// 聽聽奇美玉石瓶器音
+
+console.log(cc.convert(normalized, false));
+// 听听奇美玉石瓶器音
+```
+
+This pass uses the extended Unicode compatibility table and is separate from `normalizeCompat()`. It is useful for text
+containing radical forms, historical or allographic Han forms, and other compatibility-like characters that are not
+covered by the CJK Compatibility Ideograph ranges.
+
+Unmapped characters are preserved unchanged.
+
+### normalizeCompatExtended
+
+Apply complete compatibility normalization before conversion.
+
+```javascript
+cc.normalizeCompatExtended(text)
+```
+
+Parameters:
+
+- `text`: input string
+
+Returns:
+
+- normalized string
+
+Example:
+
+```javascript
+const cc = new OpenccWasm("t2s");
+
+const input = "天龍八部書裡的聼眾";
+const normalized = cc.normalizeCompatExtended(input);
+
+console.log(normalized);
+// 天龍八部書裡的聽眾
+
+console.log(cc.convert(normalized, false));
+// 天龙八部书里的听众
+```
+
+`normalizeCompatExtended()` combines the extended Unicode compatibility table with CJK Compatibility Ideograph
+normalization. Use this when input may contain characters handled by either normalization set.
+
+The normalization order is:
+
+1. extended Unicode compatibility normalization;
+2. CJK Compatibility Ideograph normalization.
+
+Normal OpenCC conversion does not automatically perform compatibility normalization. Call this method explicitly before
+`convert()` when complete compatibility normalization is desired.
 
 ---
 
@@ -213,12 +322,12 @@ cc.detofu(text, level)
 
 Parameters:
 
-* `text`: input string
-* `level`: `DetofuLevelWasm` threshold for the CJK extension ranges to replace
+- `text`: input string
+- `level`: `DetofuLevelWasm` threshold for the CJK extension ranges to replace
 
 Returns:
 
-* detofu-safe string
+- detofu-safe string
 
 Supported levels:
 
@@ -265,13 +374,13 @@ cc.convertDetofu(text, punctuation, level)
 
 Parameters:
 
-* `text`: input string
-* `punctuation`: whether to convert punctuation variants
-* `level`: `DetofuLevelWasm` threshold for the CJK extension ranges to replace
+- `text`: input string
+- `punctuation`: whether to convert punctuation variants
+- `level`: `DetofuLevelWasm` threshold for the CJK extension ranges to replace
 
 Returns:
 
-* converted detofu-safe string
+- converted detofu-safe string
 
 Example:
 
@@ -282,85 +391,6 @@ cc.convertDetofu("儼驂騑於上路", false, DetofuLevelWasm.ExtB);
 
 ---
 
-### setConfig
-
-```javascript
-cc.setConfig("t2s");
-```
-
-Returns:
-
-* `true` if valid
-* `false` if invalid
-
----
-
-### getConfig
-
-```javascript
-cc.getConfig();
-```
-
-Returns current config string.
-
----
-
-### isValidConfig
-
-```javascript
-OpenccWasm.isValidConfig("s2t");
-```
-
----
-
-### getSupportedConfigs
-
-```javascript
-OpenccWasm.getSupportedConfigs();
-```
-
-Returns all supported config strings.
-
-Includes `s2hkp`, `hk2sp`, `t2hkp`, and `hk2tp`.
-
----
-
-### getAvailableSlots
-
-```javascript
-const slots = OpenccWasm.getAvailableSlots();
-```
-
-Returns all canonical dictionary slot names accepted by `newWithCustomDicts` as a string array. The list is sourced from
-the core `DictSlot` definitions, so callers can use it to populate selectors or validate custom dictionary input without
-maintaining their own slot list.
-
-```javascript
-if (!OpenccWasm.getAvailableSlots().includes(slot)) {
-    throw new Error(`Unsupported dictionary slot: ${slot}`);
-}
-```
-
----
-
-### zhoCheck
-
-Detect Chinese script type.
-
-```javascript
-cc.zhoCheck(text);
-```
-
-Returns:
-
-| Value | Meaning             |
-|-------|---------------------|
-| `0`   | Unknown / mixed     |
-| `1`   | Traditional Chinese |
-| `2`   | Simplified Chinese  |
-
----
-
 ### newWithCustomDicts
 
 Construct a converter with in-memory custom dictionary pairs.
@@ -371,8 +401,8 @@ const cc = OpenccWasm.newWithCustomDicts(config, specs);
 
 Parameters:
 
-* `config`: OpenCC config string, such as `"s2t"`
-* `specs`: array of custom dictionary specs
+- `config`: OpenCC config string, such as `"s2t"`
+- `specs`: array of custom dictionary specs
 
 TypeScript-style spec shape:
 
@@ -455,14 +485,14 @@ Suffixes such as `.txt` are not accepted, even though case and surrounding white
 
 Merge contract:
 
-* Custom dictionaries are loaded from in-memory pairs only; no file I/O is involved.
-* The embedded compressed CBOR dictionary is loaded first.
-* Custom specs are applied to `DictionaryMaxlength` before `OpenCC::from_dictionary(...)`.
-* Conversion hot paths remain immutable after construction.
-* `Append` mode merges into the selected slot.
-* Duplicate or conflicting keys use last-wins semantics.
-* `Override` mode clears the selected slot first, then inserts the provided custom pairs.
-* Multiple specs are applied in array order.
+- Custom dictionaries are loaded from in-memory pairs only; no file I/O is involved.
+- The embedded compressed CBOR dictionary is loaded first.
+- Custom specs are applied to `DictionaryMaxlength` before `OpenCC::from_dictionary(...)`.
+- Conversion hot paths remain immutable after construction.
+- `Append` mode merges into the selected slot.
+- Duplicate or conflicting keys use last-wins semantics.
+- `Override` mode clears the selected slot first, then inserts the provided custom pairs.
+- Multiple specs are applied in array order.
 
 This API is useful for browser apps, user-defined terminology, database-loaded terms, generated dictionaries,
 `localStorage` or `IndexedDB` terms, testing, and embedded WASM environments. Customization happens at construction
@@ -470,6 +500,56 @@ time, not during conversion.
 
 ---
 
+## Supported Configs
+
+| Config  | Enum                     | Description                                           |
+|---------|--------------------------|-------------------------------------------------------|
+| `s2t`   | `OpenccConfigWasm.S2t`   | Simplified Chinese → Traditional Chinese              |
+| `s2tw`  | `OpenccConfigWasm.S2tw`  | Simplified Chinese → Taiwan Traditional               |
+| `s2twp` | `OpenccConfigWasm.S2twp` | Simplified Chinese → Taiwan Traditional (phrases)     |
+| `s2hk`  | `OpenccConfigWasm.S2hk`  | Simplified Chinese → Hong Kong Traditional            |
+| `s2hkp` | `OpenccConfigWasm.S2hkp` | Simplified Chinese → Hong Kong Traditional (phrases)  |
+| `t2s`   | `OpenccConfigWasm.T2s`   | Traditional Chinese → Simplified Chinese              |
+| `t2tw`  | `OpenccConfigWasm.T2tw`  | Traditional Chinese → Taiwan Traditional              |
+| `t2twp` | `OpenccConfigWasm.T2twp` | Traditional Chinese → Taiwan Traditional (phrases)    |
+| `t2hk`  | `OpenccConfigWasm.T2hk`  | Traditional Chinese → Hong Kong Traditional           |
+| `t2hkp` | `OpenccConfigWasm.T2hkp` | Traditional Chinese → Hong Kong Traditional (phrases) |
+| `tw2s`  | `OpenccConfigWasm.Tw2s`  | Taiwan Traditional → Simplified Chinese               |
+| `tw2sp` | `OpenccConfigWasm.Tw2sp` | Taiwan Traditional → Simplified Chinese (phrases)     |
+| `tw2t`  | `OpenccConfigWasm.Tw2t`  | Taiwan Traditional → Traditional Chinese              |
+| `tw2tp` | `OpenccConfigWasm.Tw2tp` | Taiwan Traditional → Traditional Chinese (phrases)    |
+| `hk2s`  | `OpenccConfigWasm.Hk2s`  | Hong Kong Traditional → Simplified Chinese            |
+| `hk2sp` | `OpenccConfigWasm.Hk2sp` | Hong Kong Traditional → Simplified Chinese (phrases)  |
+| `hk2t`  | `OpenccConfigWasm.Hk2t`  | Hong Kong Traditional → Traditional Chinese           |
+| `hk2tp` | `OpenccConfigWasm.Hk2tp` | Hong Kong Traditional → Traditional Chinese (phrases) |
+| `jp2t`  | `OpenccConfigWasm.Jp2t`  | Japanese Shinjitai → Traditional Chinese              |
+| `t2jp`  | `OpenccConfigWasm.T2jp`  | Traditional Chinese → Japanese Shinjitai              |
+
+The numeric enum values match the vendored Rust backend. Existing values are unchanged; `S2hkp = 17`, `Hk2sp = 18`,
+`T2hkp = 19`, and `Hk2tp = 20`.
+
+---
+
+## Using Config Enums
+
+```javascript
+import init, {
+    OpenccWasm,
+    OpenccConfigWasm
+} from "@laisuk/opencc-fmmseg-wasm";
+
+await init();
+
+const cc = OpenccWasm.newWithEnum(
+    OpenccConfigWasm.S2hkp
+);
+
+console.log(cc.convert("别随便录影侵犯个人隐私权", false));
+// 別隨便錄影侵犯個人私隱權
+```
+
+---
+
 ## Office / EPUB Conversion
 
 Office and EPUB conversion runs fully locally in the browser or Node.js. Files are passed in and returned as bytes;
@@ -493,14 +573,14 @@ cc.convertOfficeBytes(inputBytes, format, punctuation, keepFont)
 
 Parameters:
 
-* `inputBytes`: `Uint8Array` document bytes
-* `format`: `docx`, `xlsx`, `pptx`, `odt`, `ods`, `odp`, or `epub`
-* `punctuation`: whether to convert punctuation variants
-* `keepFont`: whether to preserve font declarations where supported
+- `inputBytes`: `Uint8Array` document bytes
+- `format`: `docx`, `xlsx`, `pptx`, `odt`, `ods`, `odp`, or `epub`
+- `punctuation`: whether to convert punctuation variants
+- `keepFont`: whether to preserve font declarations where supported
 
 Returns:
 
-* converted output bytes
+- converted output bytes
 
 The older free function remains available for compatibility:
 
@@ -649,6 +729,7 @@ opencc-fmmseg office -i input.docx -o output.docx -c s2t -p --keep-font
                               default when omitted value: all
 --keep-ids                  Preserve complete IDS expressions during conversion (default: false)
 -n, --norm-compat           Normalize CJK Compatibility Ideographs before conversion (default: false)
+-E, --norm-compat-extended  Normalize extended Unicode compatibility forms before conversion (default: false)
 -D, --custom-dict <slot:mode:file>
                             Load a custom dictionary.
                             May be specified multiple times.
@@ -708,18 +789,18 @@ The WASM-facing enum is exported as `OpenccConfigWasm`, alongside `OpenccWasm`.
 
 ## Performance Notes
 
-* WebAssembly build disables Rayon parallelism by default.
-* Dictionaries are embedded into the WASM binary.
-* Browser caching significantly improves subsequent loads.
+- WebAssembly build disables Rayon parallelism by default.
+- Dictionaries are embedded into the WASM binary.
+- Browser caching significantly improves subsequent loads.
 
 ---
 
 ## Related Projects
 
-* Rust backend: https://github.com/laisuk/opencc-fmmseg
-* C API: https://github.com/laisuk/opencc-fmmseg/tree/master/capi/opencc-fmmseg-capi
-* .NET: https://github.com/laisuk/OpenccNet
-* Python: https://github.com/laisuk/opencc_purepy
+- Rust backend: https://github.com/laisuk/opencc-fmmseg
+- C API: https://github.com/laisuk/opencc-fmmseg/tree/master/capi/opencc-fmmseg-capi
+- .NET: https://github.com/laisuk/OpenccNet
+- Python: https://github.com/laisuk/opencc_purepy
 
 ---
 

package/bin/opencc.js

@@ -58,6 +58,7 @@ Convert options:
                               default when omitted value: all
   --keep-ids                  Preserve complete IDS expressions during conversion (default: false)
   -n, --norm-compat           Normalize CJK Compatibility Ideographs before conversion (default: false)
+  -E, --norm-compat-extended  Normalize extended Unicode compatibility forms before conversion (default: false)
   -D, --custom-dict <slot:mode:file>
                               Load a custom dictionary.
                               May be specified multiple times.
@@ -88,7 +89,7 @@ Office options:
   -F, --convert-filename      Convert generated output filename stem (default: false)
   --keep-font                 Preserve font-family information (default)
   --no-keep-font              Do not preserve font-family information
-  --custom-dict <slot:mode:file>
+  -D, --custom-dict <slot:mode:file>
                               Load a custom dictionary.
                               May be specified multiple times.
                               Examples:
@@ -107,6 +108,7 @@ Examples:
   npx opencc-fmmseg convert -i a.txt -o b.txt -c t2s --detofu ext-c
   echo "⿰氵漢" | npx opencc-fmmseg convert -c t2s
   echo "⿰氵漢" | npx opencc-fmmseg convert -c t2s --keep-ids
+  echo "聼聼竒羙⽟䂖甁噐⾳" | npx opencc-fmmseg convert -c t2s -E
 
   npx opencc-fmmseg office -i a.docx -o b.docx -c s2t -p
   npx opencc-fmmseg office -i a.epub -c s2tw
@@ -189,6 +191,24 @@ function validateInputFile(filePath) {
     }
 }
 
+function ensureDistinctPaths(input, output) {
+    if (!input || !output) {
+        return;
+    }
+
+    let inputPath = path.resolve(input);
+    let outputPath = path.resolve(output);
+
+    if (process.platform === "win32") {
+        inputPath = inputPath.toLowerCase();
+        outputPath = outputPath.toLowerCase();
+    }
+
+    if (inputPath === outputPath) {
+        throw new Error("Input and output files must be different.");
+    }
+}
+
 function parseCustomDictSpec(value) {
     const first = value.indexOf(":");
     const second = value.indexOf(":", first + 1);
@@ -450,6 +470,8 @@ function parseDetofuLevel(value) {
 async function runConvert(args) {
     const input = getArg(args, "-i", "--input");
     const output = getArg(args, "-o", "--output");
+    ensureDistinctPaths(input, output);
+
     const config = getArg(args, "-c", "--config", "s2t");
     const inEnc = validateEncoding(
         getArg(args, null, "--in-enc", "utf8"),
@@ -463,6 +485,7 @@ async function runConvert(args) {
     const punct = hasFlag(args, "-p", "--punct");
     const keepIds = hasFlag(args, null, "--keep-ids");
     const normCompat = hasFlag(args, "-n", "--norm-compat");
+    const normCompatExtended = hasFlag(args, "-E", "--norm-compat-extended");
     const customDicts = getArgs(args, "-D", "--custom-dict")
         .map(parseCustomDictSpec);
 
@@ -498,7 +521,9 @@ async function runConvert(args) {
 
     let inputText = readInputText(input, inEnc);
 
-    if (normCompat) {
+    if (normCompatExtended) {
+        inputText = cc.normalizeCompatExtended(inputText);
+    } else if (normCompat) {
         inputText = cc.normalizeCompat(inputText);
     }
 
@@ -519,10 +544,20 @@ async function runConvert(args) {
         }
 
         const suffixParts = [];
-        if (normCompat) suffixParts.push("normalized");
+
+        if (normCompatExtended) {
+            suffixParts.push("norm-compat-extended");
+        } else if (normCompat) {
+            suffixParts.push("norm-compat");
+        }
+
         if (detofuEnabled) suffixParts.push("detofu");
         if (keepIds) suffixParts.push("keep-ids");
 
+        for (const spec of customDicts) {
+            suffixParts.push(`custom:${spec.slot}:${spec.mode}`);
+        }
+
         const suffix = suffixParts.length ? `, ${suffixParts.join(", ")}` : "";
         console.error(`Conversion completed (${cc.getConfig()}${suffix}): ${inFrom} -> ${outTo}`);
     }
@@ -561,6 +596,8 @@ async function runOffice(args) {
         output = applyOutputExtension(output, officeFormat);
     }
 
+    ensureDistinctPaths(input, output);
+
     const inputBytes = fs.readFileSync(input);
 
     const outputBytes = cc.convertOfficeBytes(