Merge branch 'pr/happynewplay/41'

This commit is contained in:
jhqxxx
2026-04-06 18:23:23 +08:00
33 changed files with 11898 additions and 23 deletions
+8
View File
@@ -21,3 +21,11 @@ bak
demos
benchmarks
lib/*.lib
lib/*.pdb
findings.md
modify_test.md
progress.md
task_plan.md
Generated
-2
View File
@@ -1235,8 +1235,6 @@ dependencies = [
[[package]]
name = "esaxx-rs"
version = "0.1.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d817e038c30374a4bcb22f94d0a8a0e216958d4c3dcde369b1439fec4bdda6e6"
dependencies = [
"cc",
]
+5
View File
@@ -45,6 +45,9 @@ sentencepiece = "0.13.1"
ahash = "0.8.12"
derive_builder = "0.20.2"
[patch.crates-io]
esaxx-rs = { path = "vendor/esaxx-rs" }
[features]
flash-attn = ["candle-flash-attn"]
cuda = ["candle-nn/cuda", "candle-core/cuda", "candle-transformers/cuda"]
@@ -55,3 +58,5 @@ ffmpeg = ["ffmpeg-next"]
needless_range_loop = "allow"
single_range_in_vec_init = "allow"
manual_div_ceil = "allow"
[dev-dependencies]
+15
View File
@@ -119,6 +119,21 @@ aha cli -m Qwen/Qwen3-ASR-0.6B
# Run inference directly (without starting service)
aha run -m Qwen/Qwen3-ASR-0.6B -i "audio.wav"
# Run local all-MiniLM-L6-v2 embedding (native safetensors)
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --weight-path D:\model_download\all-MiniLM-L6-v2
# Run local all-MiniLM-L6-v2 embedding (GGUF)
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --artifact-format gguf --gguf-path D:\model_download\All-MiniLM-L6-v2-Embedding-GGUF --tokenizer-dir D:\model_download\all-MiniLM-L6-v2
# Run local all-MiniLM-L6-v2 embedding (ONNX)
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --artifact-format onnx --onnx-path D:\model_download\all-MiniLM-L6-v2\onnx --tokenizer-dir D:\model_download\all-MiniLM-L6-v2
# Run local GLM-OCR (GGUF)
aha run -m glm-ocr -i .\assets\img\ocr_test1.png --artifact-format gguf --gguf-path D:\model_download\GLM-OCR-GGUF
# Run local GLM-OCR (ONNX)
aha run -m glm-ocr -i .\assets\img\ocr_test1.png --artifact-format onnx --onnx-path D:\model_download\GLM-OCR-ONNX --tokenizer-dir D:\model_download\GLM-OCR-ONNX
# Start service only (model already downloaded)
aha serv -m Qwen/Qwen3-ASR-0.6B -p 10100
+15
View File
@@ -119,6 +119,21 @@ aha cli -m Qwen/Qwen3-ASR-0.6B
# 直接运行推理(无需启动服务)
aha run -m Qwen/Qwen3-ASR-0.6B -i "audio.wav"
# 本地运行 all-MiniLM-L6-v2 向量模型(原生 safetensors
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --weight-path D:\model_download\all-MiniLM-L6-v2
# 本地运行 all-MiniLM-L6-v2 向量模型(GGUF
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --artifact-format gguf --gguf-path D:\model_download\All-MiniLM-L6-v2-Embedding-GGUF --tokenizer-dir D:\model_download\all-MiniLM-L6-v2
# 本地运行 all-MiniLM-L6-v2 向量模型(ONNX
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --artifact-format onnx --onnx-path D:\model_download\all-MiniLM-L6-v2\onnx --tokenizer-dir D:\model_download\all-MiniLM-L6-v2
# 本地运行 GLM-OCRGGUF
aha run -m glm-ocr -i .\assets\img\ocr_test1.png --artifact-format gguf --gguf-path D:\model_download\GLM-OCR-GGUF
# 本地运行 GLM-OCRONNX
aha run -m glm-ocr -i .\assets\img\ocr_test1.png --artifact-format onnx --onnx-path D:\model_download\GLM-OCR-ONNX --tokenizer-dir D:\model_download\GLM-OCR-ONNX
# 仅启动服务(模型已下载)
aha serv -m Qwen/Qwen3-ASR-0.6B -p 10100
+39 -5
View File
@@ -66,6 +66,11 @@ aha cli -m Qwen/Qwen3-VL-2B-Instruct --weight-path /path/to/model
# use gguf-path and mmproj-path
aha cli -m qwen3.5-gguf --gguf-path /path/to/xxx.gguf --mmproj-path /path/to/mmproj-xxx.gguf
# run service with ONNX artifact
aha cli -m qwen3-embedding-0.6b --artifact-format onnx \
--onnx-path /path/to/Qwen3-Embedding-0.6B-ONNX \
--tokenizer-dir /path/to/Qwen3-Embedding-0.6B-ONNX
```
### run - Direct model inference
@@ -117,6 +122,9 @@ aha run -m FunAudioLLM/Fun-ASR-Nano-2512 -i "语音转写:" -i "audio.wav" --w
# qwen3 text generation (single input)
aha run -m Qwen/Qwen3-0.6B -i "你好" --weight-path /path/to/model
# qwen3 GGUF text generation (single input)
aha run -m qwen3-0.6b -i "hello" --artifact-format gguf --gguf-path /path/to/Qwen3-0.6B-Q8_0.gguf
# qwen2.5vl image understanding (two inputs: prompt text + image file)
aha run -m Qwen/Qwen2.5-VL-3B-Instruct -i "请分析图片并提取所有可见文本内容,按从左到右、从上到下的布局,返回纯文本" -i "image.jpg" --weight-path /path/to/model
@@ -130,6 +138,11 @@ aha run -m qwen3.5-gguf -i 你如何看待AI --gguf-path /path/to/xxx.gguf
aha run -m qwen3.5-gguf -i 提取图片中的文本 -i https://ai.bdstatic.com/file/C56CC9B274CF460CA33
63E59ECD94423 --gguf-path /path/to/xxx.gguf --mmproj-path /path/to/mmproj-xxx.gguf
# Qwen3.5 ONNX text-only generation
aha run -m qwen3.5-0.8b -i "hello" --artifact-format onnx \
--onnx-path /path/to/Qwen3.5-0.8B-ONNX \
--tokenizer-dir /path/to/Qwen3.5-0.8B-ONNX
```
### serv - Start service
@@ -154,6 +167,9 @@ aha serv [OPTIONS] --model <MODEL> [--weight-path <WEIGHT_PATH>] [--gguf-path <G
| `--allow-remote-shutdown` | Allow remote shutdown requests (not recommended) | false |
| `--gguf-path <GGUF_PATH>` | Local GGUF model weight pathrequired when using GGUF models | - |
| `--mmproj-path <MMPROJ_PATH>` | Local mmproj GGUF weight pathoptionalIf not specified, the module will not be loaded | - |
| `--onnx-path <ONNX_PATH>` | Local ONNX model directory/file pathrequired when using ONNX models | - |
| `--tokenizer-dir <TOKENIZER_DIR>` | Tokenizer/config directory for GGUF/ONNX | - |
| `--artifact-format <ARTIFACT_FORMAT>` | Artifact format (`auto|safetensors|gguf|onnx`) | auto |
**Examples:**
@@ -395,6 +411,20 @@ After the service starts, the following API endpoints are available:
- **Format**: OpenAI Chat Completion format
- **Streaming Support**: No
### Embeddings Endpoint
- **Endpoint**: `POST /embeddings` or `POST /v1/embeddings`
- **Function**: Text embedding generation
- **Supported Models**: Qwen3-Embedding family
- **Format**: OpenAI embeddings format
- **Streaming Support**: No
### Rerank Endpoint
- **Endpoint**: `POST /rerank` or `POST /v1/rerank`
- **Function**: Query-document reranking
- **Supported Models**: Qwen3-Reranker family
- **Format**: Rerank JSON response (`results[index,relevance_score,document]`)
- **Streaming Support**: No
### Shutdown Endpoint
- **Endpoint**: `POST /shutdown`
- **Function**: Gracefully shut down the server
@@ -404,15 +434,19 @@ After the service starts, the following API endpoints are available:
## Notes
1. **serv subcommand requires `--weight-path`**: Since the `serv` subcommand does not download models, you must specify the path to an already downloaded model via `--weight-path`.
1. **Local-path rule for GGUF/ONNX**: GGUF and ONNX artifacts are local-path only; use `--gguf-path` or `--onnx-path`. Remote download management is only for safetensors models.
2. **Download retry mechanism**: By default, retries 3 times, waiting 2 seconds after each failure before retrying. You can adjust the retry count with `--download-retries`.
2. **Artifact selection**: `--artifact-format auto` uses model default; you can force `safetensors|gguf|onnx` explicitly.
3. **Default save directory**: Models are saved to `~/.aha/` directory by default, which can be customized via `--save-dir` or `-s` parameter.
3. **Tokenizer directory**: For GGUF/ONNX, if tokenizer files are not colocated with model files, set `--tokenizer-dir`.
4. **Port occupation**: Ensure the specified port is not occupied before starting the service. The default port is 10100.
4. **Download retry mechanism**: By default, retries 3 times, waiting 2 seconds after each failure before retrying. You can adjust the retry count with `--download-retries`.
5. **Permission issues**: If saving to a system directory (such as `/data/models`), ensure you have the corresponding write permissions.
5. **Default save directory**: Models are saved to `~/.aha/` directory by default, which can be customized via `--save-dir` or `-s` parameter.
6. **Port occupation**: Ensure the specified port is not occupied before starting the service. The default port is 10100.
7. **Permission issues**: If saving to a system directory (such as `/data/models`), ensure you have the corresponding write permissions.
## Getting Help
+39 -6
View File
@@ -66,6 +66,11 @@ aha cli -m Qwen/Qwen3-VL-2B-Instruct --weight-path /path/to/model
# 指定gguf-path和mmproj-path
aha cli -m qwen3.5-gguf --gguf-path /path/to/xxx.gguf --mmproj-path /path/to/mmproj-xxx.gguf
# 使用 ONNX 模型启动服务
aha cli -m qwen3-embedding-0.6b --artifact-format onnx \
--onnx-path /path/to/Qwen3-Embedding-0.6B-ONNX \
--tokenizer-dir /path/to/Qwen3-Embedding-0.6B-ONNX
```
### run - 直接模型推理
@@ -117,6 +122,9 @@ aha run -m FunAudioLLM/Fun-ASR-Nano-2512 -i "语音转写:" -i "audio.wav" --w
# qwen3 文本生成(单个输入)
aha run -m Qwen/Qwen3-0.6B -i "你好" --weight-path /path/to/model
# qwen3 GGUF 文本生成(单个输入)
aha run -m qwen3-0.6b -i "你好" --artifact-format gguf --gguf-path /path/to/Qwen3-0.6B-Q8_0.gguf
# qwen2.5vl 图像理解(两个输入:提示文本 + 图片文件)
aha run -m Qwen/Qwen2.5-VL-3B-Instruct -i "请分析图片并提取所有可见文本内容,按从左到右、从上到下的布局,返回纯文本" -i "image.jpg" --weight-path /path/to/model
@@ -129,6 +137,11 @@ aha run -m qwen3.5-gguf -i 你如何看待AI --gguf-path /path/to/xxx.gguf
# Qwen3.5-GGUF 有mmproj (两个输入:提示文本 + 文件)
aha run -m qwen3.5-gguf -i 提取图片中的文本 -i https://ai.bdstatic.com/file/C56CC9B274CF460CA33
63E59ECD94423 --gguf-path /path/to/xxx.gguf --mmproj-path /path/to/mmproj-xxx.gguf
# Qwen3.5 ONNX 文本生成(text-only
aha run -m qwen3.5-0.8b -i "你好" --artifact-format onnx \
--onnx-path /path/to/Qwen3.5-0.8B-ONNX \
--tokenizer-dir /path/to/Qwen3.5-0.8B-ONNX
```
### serv - 启动服务
@@ -139,7 +152,9 @@ GGUF/ONNX模型必须指定本地文件路径
**语法:**
```bash
aha serv [OPTIONS] --model <MODEL> [--weight-path <WEIGHT_PATH>] [--gguf-path <GGUF_PATH>] [--mmproj-path <MMPROJ_PATH>]
aha serv [OPTIONS] --model <MODEL> [--weight-path <WEIGHT_PATH>] [--gguf-path <GGUF_PATH>] \
[--mmproj-path <MMPROJ_PATH>] [--onnx-path <ONNX_PATH>] [--tokenizer-dir <TOKENIZER_DIR>] \
[--artifact-format <ARTIFACT_FORMAT>]
```
**选项:**
@@ -396,6 +411,20 @@ aha cli -m Qwen/Qwen3-VL-2B-Instruct -a 0.0.0.0 -p 8080
- **格式**: OpenAI Chat Completion 格式
- **流式支持**: 不支持
### Embeddings 接口
- **端点**: `POST /embeddings``POST /v1/embeddings`
- **功能**: 文本向量生成
- **支持模型**: Qwen3-Embedding 系列
- **格式**: OpenAI embeddings 格式
- **流式支持**: 不支持
### Rerank 接口
- **端点**: `POST /rerank``POST /v1/rerank`
- **功能**: query/document 重排打分
- **支持模型**: Qwen3-Reranker 系列
- **格式**: Rerank JSON`results[index,relevance_score,document]`
- **流式支持**: 不支持
### 关机接口
- **端点**: `POST /shutdown`
- **功能**: 优雅地关闭服务器
@@ -405,15 +434,19 @@ aha cli -m Qwen/Qwen3-VL-2B-Instruct -a 0.0.0.0 -p 8080
## 注意事项
1. **serv 子命令必须指定 `--weight-path`**:由于 `serv` 子命令不下载模型,必须通过 `--weight-path` 指定已下载的模型路径
1. **GGUF/ONNX 仅支持本地路径**:请使用 `--gguf-path``--onnx-path`。自动下载管理仅适用于 safetensors 模型
2. **下载重试机制**:默认重试 3 次,每次失败后等待 2 秒再重试。可通过 `--download-retries` 调整重试次数
2. **制品格式选择**`--artifact-format auto` 使用模型默认格式,也可显式指定 `safetensors|gguf|onnx`
3. **默认保存目录**:模型默认保存到 `~/.aha/` 目录下,可通过 `--save-dir``-s` 参数自定义
3. **tokenizer 目录**GGUF/ONNX 若未与 tokenizer/config 同目录,请额外指定 `--tokenizer-dir`
4. **端口占用**:启动服务前确保指定的端口未被占用,默认端口为 10100
4. **下载重试机制**:默认重试 3 次,每次失败后等待 2 秒再重试。可通过 `--download-retries` 调整重试次数
5. **权限问题**:如果保存到系统目录(如 `/data/models`),确保有相应的写入权限
5. **默认保存目录**:模型默认保存到 `~/.aha/` 目录下,可通过 `--save-dir``-s` 参数自定义
6. **端口占用**:启动服务前确保指定的端口未被占用,默认端口为 10100。
7. **权限问题**:如果保存到系统目录(如 `/data/models`),确保有相应的写入权限。
## 获取帮助
+70
View File
@@ -51,6 +51,23 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔
| **LFM2.5-1.2B-Instruct** | 1.2B | LiquidAI/LFM2.5-1.2B-Instruct | [lfm1.0](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct/blob/main/LICENSE) |
## Embedding
| Model | Parameters | Description | License |
|-------|-----------|-------------|---------|
| **Qwen3-Embedding-0.6B** | 0.6B | Text embedding (safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Qwen3-Embedding-4B** | 4B | Text embedding (safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Qwen3-Embedding-8B** | 8B | Text embedding (safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **all-MiniLM-L6-v2** | 22M | Sentence-transformers embedding (safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/blob/main/LICENSE) |
## Reranker
| Model | Parameters | Description | License |
|-------|-----------|-------------|---------|
| **Qwen3-Reranker-0.6B** | 0.6B | Text reranking (embedding-similarity baseline, safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Qwen3-Reranker-4B** | 4B | Text reranking (embedding-similarity baseline, safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Qwen3-Reranker-8B** | 8B | Text reranking (embedding-similarity baseline, safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
## Vision & Multimodal
| Model | Parameters | Model Id | License |
@@ -71,6 +88,8 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔
| **GLM-OCR** | 8 | ZhipuAI/GLM-OCR | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) |
GLM-OCR local artifacts: `safetensors`, `gguf`, `onnx`
## Speech Recognition (ASR)
| Model | Parameters | Language | Model Id | License |
@@ -98,6 +117,57 @@ Models are sourced from:
- [Hugging Face](https://huggingface.co) - Primary model hub
- [ModelScope](https://modelscope.cn) - Chinese model hub
## Registered Repositories (Not Runtime-Integrated Yet)
The following repositories are now cataloged for future integration, but are **not** directly runnable in current `aha` runtime yet:
### MLX / Format-Specific Variants
- Jackrong/MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit
- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit
- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-6bit
- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-8bit
- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit
- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-6bit
- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-8bit
### Embedding Models
- google/embeddinggemma-300m
- ggml-org/embeddinggemma-300M-GGUF
- onnx-community/embeddinggemma-300m-ONNX
- unsloth/embeddinggemma-300m-GGUF
- onnx-community/Qwen3-Embedding-0.6B-ONNX
- Qwen/Qwen3-Embedding-0.6B-GGUF
- onnx-community/Qwen3-Embedding-4B-ONNX
- Qwen/Qwen3-Embedding-4B-GGUF
- Qwen/Qwen3-Embedding-8B-GGUF
- onnx-community/Qwen3-Embedding-8B-ONNX
- perplexity-ai/pplx-embed-v1-0.6b
- nomic-ai/nomic-embed-text-v2-moe
- nomic-ai/nomic-embed-text-v2-moe-GGUF
- jinaai/jina-embeddings-v5-text-small
- jinaai/jina-embeddings-v5-text-nano
- jinaai/jina-embeddings-v5-text-small-text-matching
- jinaai/jina-embeddings-v5-text-small-text-matching-GGUF
- sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
### Reranker Models
- BAAI/bge-reranker-v2-m3
- ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF
### ONNX Repositories
- onnx-community/GLM-OCR-ONNX
- onnx-community/Qwen3-Reranker-0.6B-ONNX
- onnx-community/Qwen3.5-2B-ONNX
- onnx-community/Qwen3.5-4B-ONNX
- onnx-community/Qwen3.5-0.8B-ONNX
- onnx-community/Qwen3-VL-2B-Instruct-ONNX
- onnx-community/ONNX_Qwen3-Embedding-0.6B
- onnx-community/Nanbeige4.1-3B-ONNX
- onnx-community/Qwen3-Embedding-8B-ONNX
- onnx-community/Qwen3-Embedding-4B-ONNX
- onnx-community/bge-reranker-v2-m3-ONNX
- onnx-community/all-MiniLM-L6-v2-ONNX
## Adding New Models
See [Development Guide](./development.md) for instructions on adding new model integrations.
+70
View File
@@ -50,6 +50,23 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔
| **LFM2-1.2B** | 1.2B | LiquidAI/LFM2-1.2B | [lfm1.0](https://huggingface.co/LiquidAI/LFM2-1.2B/blob/main/LICENSE) |
| **LFM2.5-1.2B-Instruct** | 1.2B | LiquidAI/LFM2.5-1.2B-Instruct | [lfm1.0](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct/blob/main/LICENSE) |
## Embedding
| 模型 | 参数量 | 描述 | 开源协议 |
|------|--------|------|---------|
| **Qwen3-Embedding-0.6B** | 0.6B | 文本向量(safetensors / gguf / onnx | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Qwen3-Embedding-4B** | 4B | 文本向量(safetensors / gguf / onnx | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Qwen3-Embedding-8B** | 8B | 文本向量(safetensors / gguf / onnx | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **all-MiniLM-L6-v2** | 22M | sentence-transformers 文本向量(safetensors / gguf / onnx | [Apache 2.0](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/blob/main/LICENSE) |
## Reranker
| 模型 | 参数量 | 描述 | 开源协议 |
|------|--------|------|---------|
| **Qwen3-Reranker-0.6B** | 0.6B | 文本重排(embedding-similarity 基线,safetensors / gguf / onnx | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Qwen3-Reranker-4B** | 4B | 文本重排(embedding-similarity 基线,safetensors / gguf / onnx | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
| **Qwen3-Reranker-8B** | 8B | 文本重排(embedding-similarity 基线,safetensors / gguf / onnx | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) |
## 视觉与多模态
| 模型 | 参数量 | 模型id | 开源协议 |
@@ -69,6 +86,8 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔
| **DeepSeek-OCR** | 多语言 | deepseek-ai/DeepSeek-OCR <br> deepseek-ai/DeepSeek-OCR-2 | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) |
| **GLM-OCR** | 8 | ZhipuAI/GLM-OCR | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) |
GLM-OCR 本地制品格式:`safetensors``gguf``onnx`
## 语音识别 (ASR)
| 模型 | 参数量 | 语言 | 模型id | 开源协议 |
@@ -97,6 +116,57 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔
- [Hugging Face](https://huggingface.co) - 主模型中心
- [ModelScope](https://modelscope.cn) - 中文模型中心
## 已收录仓库(当前运行时暂未直接接入)
以下仓库已纳入项目模型目录,但当前 `aha` 运行时尚不能直接推理:
### MLX / 特定格式变体
- Jackrong/MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit
- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit
- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-6bit
- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-8bit
- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit
- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-6bit
- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-8bit
### Embedding 模型
- google/embeddinggemma-300m
- ggml-org/embeddinggemma-300M-GGUF
- onnx-community/embeddinggemma-300m-ONNX
- unsloth/embeddinggemma-300m-GGUF
- onnx-community/Qwen3-Embedding-0.6B-ONNX
- Qwen/Qwen3-Embedding-0.6B-GGUF
- onnx-community/Qwen3-Embedding-4B-ONNX
- Qwen/Qwen3-Embedding-4B-GGUF
- Qwen/Qwen3-Embedding-8B-GGUF
- onnx-community/Qwen3-Embedding-8B-ONNX
- perplexity-ai/pplx-embed-v1-0.6b
- nomic-ai/nomic-embed-text-v2-moe
- nomic-ai/nomic-embed-text-v2-moe-GGUF
- jinaai/jina-embeddings-v5-text-small
- jinaai/jina-embeddings-v5-text-nano
- jinaai/jina-embeddings-v5-text-small-text-matching
- jinaai/jina-embeddings-v5-text-small-text-matching-GGUF
- sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
### Reranker 模型
- BAAI/bge-reranker-v2-m3
- ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF
### ONNX 仓库
- onnx-community/GLM-OCR-ONNX
- onnx-community/Qwen3-Reranker-0.6B-ONNX
- onnx-community/Qwen3.5-2B-ONNX
- onnx-community/Qwen3.5-4B-ONNX
- onnx-community/Qwen3.5-0.8B-ONNX
- onnx-community/Qwen3-VL-2B-Instruct-ONNX
- onnx-community/ONNX_Qwen3-Embedding-0.6B
- onnx-community/Nanbeige4.1-3B-ONNX
- onnx-community/Qwen3-Embedding-8B-ONNX
- onnx-community/Qwen3-Embedding-4B-ONNX
- onnx-community/bge-reranker-v2-m3-ONNX
- onnx-community/all-MiniLM-L6-v2-ONNX
## 添加新模型
参见 [开发指南](./development.zh-CN.md) 了解添加新模型集成的说明。
+3 -1
View File
@@ -27,7 +27,9 @@ impl ExecModel for FunASRNanoExec {
println!("Time elapsed in load model is: {:?}", i_duration);
// Create ChatCompletionParameters for ASR
let url = &input[1];
let url = input.get(1).ok_or_else(|| {
anyhow::anyhow!("fun-asr-nano requires a second input: audio path or URL")
})?;
let input_url = if url.starts_with("http://")
|| url.starts_with("https://")
|| url.starts_with("file://")
+3 -1
View File
@@ -28,7 +28,9 @@ impl ExecModel for GlmASRNanoExec {
// Create ChatCompletionParameters for ASR
// Input should be an audio file path
let url = &input[1];
let url = input.get(1).ok_or_else(|| {
anyhow::anyhow!("glm-asr-nano requires a second input: audio path or URL")
})?;
let input_url = if url.starts_with("http://")
|| url.starts_with("https://")
|| url.starts_with("file://")
+3 -1
View File
@@ -19,7 +19,9 @@ impl ExecModel for Qwen2_5VLExec {
} else {
input_text.clone()
};
let url = &input[1];
let url = input.get(1).ok_or_else(|| {
anyhow::anyhow!("qwen2.5vl requires a second input: image path or URL")
})?;
let input_url = if url.starts_with("http://")
|| url.starts_with("https://")
|| url.starts_with("file://")
+10 -7
View File
@@ -98,14 +98,16 @@ impl<'a> GenerateModel for ModelInstance<'a> {
ModelInstance::Lfm2VL(model) => model.generate(mes),
ModelInstance::Qwen2_5VL(model) => model.generate(mes),
ModelInstance::Qwen3(model) => model.generate(mes),
ModelInstance::Qwen3_5(model) => model.generate(mes),
ModelInstance::Qwen3Embedding(_) => {
Err(anyhow!("embedding model does not support chat completions"))
}
ModelInstance::Qwen3ASR(model) => model.generate(mes),
ModelInstance::Qwen3Reranker(_) => {
Err(anyhow!("reranker model does not support chat completions"))
}
ModelInstance::Qwen3_5(model) => model.generate(mes),
ModelInstance::Qwen3ASR(model) => model.generate(mes),
ModelInstance::Qwen3VL(model) => model.generate(mes),
ModelInstance::DeepSeekOCR(model) => model.generate(mes),
ModelInstance::HunyuanOCR(model) => model.generate(mes),
@@ -138,14 +140,15 @@ impl<'a> GenerateModel for ModelInstance<'a> {
ModelInstance::Lfm2VL(model) => model.generate_stream(mes),
ModelInstance::Qwen2_5VL(model) => model.generate_stream(mes),
ModelInstance::Qwen3(model) => model.generate_stream(mes),
ModelInstance::Qwen3_5(model) => model.generate_stream(mes),
ModelInstance::Qwen3ASR(model) => model.generate_stream(mes),
ModelInstance::Qwen3Embedding(_) => Err(anyhow!(
"embedding model does not support streaming chat completions"
)),
ModelInstance::Qwen3Reranker(_) => {
Err(anyhow!("reranker model does not support chat completions"))
}
ModelInstance::Qwen3Reranker(_) => Err(anyhow!(
"reranker model does not support streaming chat completions"
)),
ModelInstance::Qwen3_5(model) => model.generate_stream(mes),
ModelInstance::Qwen3ASR(model) => model.generate_stream(mes),
ModelInstance::Qwen3VL(model) => model.generate_stream(mes),
ModelInstance::DeepSeekOCR(model) => model.generate_stream(mes),
ModelInstance::HunyuanOCR(model) => model.generate_stream(mes),
+1
View File
@@ -0,0 +1 @@
{"v":1}
+6
View File
@@ -0,0 +1,6 @@
{
"git": {
"sha1": "dacdea35f18b551cb23bd3bf6ab58363784a94f4"
},
"path_in_vcs": ""
}
+25
View File
@@ -0,0 +1,25 @@
name: build
on: [push, pull_request]
jobs:
build:
runs-on: ${{matrix.os}}
strategy:
fail-fast: true
matrix:
os: [macos-latest, ubuntu-latest, windows-latest]
steps:
- uses: actions/checkout@v2
- name: Check formatting
run: |
rustup component add rustfmt
rustup component add clippy
cargo fmt -- --check
cargo clippy --all-features --verbose -- -Dwarnings
- name: Build
run: cargo build --verbose
- name: Run tests
run: cargo test --all-features
Generated Vendored
+678
View File
@@ -0,0 +1,678 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3
[[package]]
name = "aho-corasick"
version = "1.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ea5d730647d4fadd988536d06fecce94b7b4f2a7efdae548f1cf4b63205518ab"
dependencies = [
"memchr",
]
[[package]]
name = "anes"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4b46cbb362ab8752921c97e041f5e366ee6297bd428a31275b9fcf1e380f7299"
[[package]]
name = "anstyle"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7079075b41f533b8c61d2a4d073c4676e1f8b249ff94a393b0595db304e0dd87"
[[package]]
name = "autocfg"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
[[package]]
name = "bitflags"
version = "2.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b4682ae6287fcf752ecaabbfcc7b6f9b72aa33933dc23a554d853aea8eea8635"
[[package]]
name = "bumpalo"
version = "3.14.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7f30e7476521f6f8af1a1c4c0b8cc94f0bee37d91763d0ca2665f299b6cd8aec"
[[package]]
name = "cast"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
[[package]]
name = "cc"
version = "1.0.83"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f1174fb0b6ec23863f8b971027804a42614e347eafb0a95bf0b12cdae21fc4d0"
dependencies = [
"libc",
]
[[package]]
name = "cfg-if"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]]
name = "ciborium"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "effd91f6c78e5a4ace8a5d3c0b6bfaec9e2baaef55f3efc00e45fb2e477ee926"
dependencies = [
"ciborium-io",
"ciborium-ll",
"serde",
]
[[package]]
name = "ciborium-io"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cdf919175532b369853f5d5e20b26b43112613fd6fe7aee757e35f7a44642656"
[[package]]
name = "ciborium-ll"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "defaa24ecc093c77630e6c15e17c51f5e187bf35ee514f4e2d67baaa96dae22b"
dependencies = [
"ciborium-io",
"half",
]
[[package]]
name = "clap"
version = "4.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d04704f56c2cde07f43e8e2c154b43f216dc5c92fc98ada720177362f953b956"
dependencies = [
"clap_builder",
]
[[package]]
name = "clap_builder"
version = "4.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0e231faeaca65ebd1ea3c737966bf858971cd38c3849107aa3ea7de90a804e45"
dependencies = [
"anstyle",
"clap_lex",
]
[[package]]
name = "clap_lex"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cd7cc57abe963c6d3b9d8be5b06ba7c8957a930305ca90304f24ef040aa6f961"
[[package]]
name = "criterion"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f2b12d017a929603d80db1831cd3a24082f8137ce19c69e6447f54f5fc8d692f"
dependencies = [
"anes",
"cast",
"ciborium",
"clap",
"criterion-plot",
"is-terminal",
"itertools",
"num-traits",
"once_cell",
"oorandom",
"plotters",
"rayon",
"regex",
"serde",
"serde_derive",
"serde_json",
"tinytemplate",
"walkdir",
]
[[package]]
name = "criterion-plot"
version = "0.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
dependencies = [
"cast",
"itertools",
]
[[package]]
name = "crossbeam-deque"
version = "0.8.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ce6fd6f855243022dcecf8702fef0c297d4338e226845fe067f6341ad9fa0cef"
dependencies = [
"cfg-if",
"crossbeam-epoch",
"crossbeam-utils",
]
[[package]]
name = "crossbeam-epoch"
version = "0.9.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ae211234986c545741a7dc064309f67ee1e5ad243d0e48335adc0484d960bcc7"
dependencies = [
"autocfg",
"cfg-if",
"crossbeam-utils",
"memoffset",
"scopeguard",
]
[[package]]
name = "crossbeam-utils"
version = "0.8.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a22b2d63d4d1dc0b7f1b6b2747dd0088008a9be28b6ddf0b1e7d335e3037294"
dependencies = [
"cfg-if",
]
[[package]]
name = "either"
version = "1.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a26ae43d7bcc3b814de94796a5e736d4029efb0ee900c12e2d54c993ad1a1e07"
[[package]]
name = "errno"
version = "0.3.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "add4f07d43996f76ef320709726a556a9d4f965d9410d8d0271132d2f8293480"
dependencies = [
"errno-dragonfly",
"libc",
"windows-sys",
]
[[package]]
name = "errno-dragonfly"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aa68f1b12764fab894d2755d2518754e71b4fd80ecfb822714a1206c2aab39bf"
dependencies = [
"cc",
"libc",
]
[[package]]
name = "esaxx-rs"
version = "0.1.10"
dependencies = [
"cc",
"criterion",
]
[[package]]
name = "half"
version = "1.8.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eabb4a44450da02c90444cf74558da904edde8fb4e9035a9a6a4e15445af0bd7"
[[package]]
name = "hermit-abi"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d77f7ec81a6d05a3abb01ab6eb7590f6083d08449fe5a1c8b1e620283546ccb7"
[[package]]
name = "is-terminal"
version = "0.4.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cb0889898416213fab133e1d33a0e5858a48177452750691bde3666d0fdbaf8b"
dependencies = [
"hermit-abi",
"rustix",
"windows-sys",
]
[[package]]
name = "itertools"
version = "0.10.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473"
dependencies = [
"either",
]
[[package]]
name = "itoa"
version = "1.0.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "af150ab688ff2122fcef229be89cb50dd66af9e01a4ff320cc137eecc9bacc38"
[[package]]
name = "js-sys"
version = "0.3.64"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c5f195fe497f702db0f318b07fdd68edb16955aed830df8363d837542f8f935a"
dependencies = [
"wasm-bindgen",
]
[[package]]
name = "libc"
version = "0.2.148"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9cdc71e17332e86d2e1d38c1f99edcb6288ee11b815fb1a4b049eaa2114d369b"
[[package]]
name = "linux-raw-sys"
version = "0.4.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3852614a3bd9ca9804678ba6be5e3b8ce76dfc902cae004e3e0c44051b6e88db"
[[package]]
name = "log"
version = "0.4.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b5e6163cb8c49088c2c36f57875e58ccd8c87c7427f7fbd50ea6710b2f3f2e8f"
[[package]]
name = "memchr"
version = "2.6.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f665ee40bc4a3c5590afb1e9677db74a508659dfd71e126420da8274909a0167"
[[package]]
name = "memoffset"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a634b1c61a95585bd15607c6ab0c4e5b226e695ff2800ba0cdccddf208c406c"
dependencies = [
"autocfg",
]
[[package]]
name = "num-traits"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f30b0abd723be7e2ffca1272140fac1a2f084c77ec3e123c192b66af1ee9e6c2"
dependencies = [
"autocfg",
]
[[package]]
name = "once_cell"
version = "1.18.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dd8b5dd2ae5ed71462c540258bedcb51965123ad7e7ccf4b9a8cafaa4a63576d"
[[package]]
name = "oorandom"
version = "11.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0ab1bc2a289d34bd04a330323ac98a1b4bc82c9d9fcb1e66b63caa84da26b575"
[[package]]
name = "plotters"
version = "0.3.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d2c224ba00d7cadd4d5c660deaf2098e5e80e07846537c51f9cfa4be50c1fd45"
dependencies = [
"num-traits",
"plotters-backend",
"plotters-svg",
"wasm-bindgen",
"web-sys",
]
[[package]]
name = "plotters-backend"
version = "0.3.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9e76628b4d3a7581389a35d5b6e2139607ad7c75b17aed325f210aa91f4a9609"
[[package]]
name = "plotters-svg"
version = "0.3.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "38f6d39893cca0701371e3c27294f09797214b86f1fb951b89ade8ec04e2abab"
dependencies = [
"plotters-backend",
]
[[package]]
name = "proc-macro2"
version = "1.0.67"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3d433d9f1a3e8c1263d9456598b16fec66f4acc9a74dacffd35c7bb09b3a1328"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.33"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5267fca4496028628a95160fc423a33e8b2e6af8a5302579e322e4b520293cae"
dependencies = [
"proc-macro2",
]
[[package]]
name = "rayon"
version = "1.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c27db03db7734835b3f53954b534c91069375ce6ccaa2e065441e07d9b6cdb1"
dependencies = [
"either",
"rayon-core",
]
[[package]]
name = "rayon-core"
version = "1.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5ce3fb6ad83f861aac485e76e1985cd109d9a3713802152be56c3b1f0e0658ed"
dependencies = [
"crossbeam-deque",
"crossbeam-utils",
]
[[package]]
name = "regex"
version = "1.9.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ebee201405406dbf528b8b672104ae6d6d63e6d118cb10e4d51abbc7b58044ff"
dependencies = [
"aho-corasick",
"memchr",
"regex-automata",
"regex-syntax",
]
[[package]]
name = "regex-automata"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "59b23e92ee4318893fa3fe3e6fb365258efbfe6ac6ab30f090cdcbb7aa37efa9"
dependencies = [
"aho-corasick",
"memchr",
"regex-syntax",
]
[[package]]
name = "regex-syntax"
version = "0.7.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dbb5fb1acd8a1a18b3dd5be62d25485eb770e05afb408a9627d14d451bae12da"
[[package]]
name = "rustix"
version = "0.38.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f25469e9ae0f3d0047ca8b93fc56843f38e6774f0914a107ff8b41be8be8e0b7"
dependencies = [
"bitflags",
"errno",
"libc",
"linux-raw-sys",
"windows-sys",
]
[[package]]
name = "ryu"
version = "1.0.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1ad4cc8da4ef723ed60bced201181d83791ad433213d8c24efffda1eec85d741"
[[package]]
name = "same-file"
version = "1.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
dependencies = [
"winapi-util",
]
[[package]]
name = "scopeguard"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
[[package]]
name = "serde"
version = "1.0.188"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cf9e0fcba69a370eed61bcf2b728575f726b50b55cba78064753d708ddc7549e"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.188"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4eca7ac642d82aa35b60049a6eccb4be6be75e599bd2e9adb5f875a737654af2"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serde_json"
version = "1.0.107"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6b420ce6e3d8bd882e9b243c6eed35dbc9a6110c9769e74b584e0d68d1f20c65"
dependencies = [
"itoa",
"ryu",
"serde",
]
[[package]]
name = "syn"
version = "2.0.37"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7303ef2c05cd654186cb250d29049a24840ca25d2747c25c0381c8d9e2f582e8"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "tinytemplate"
version = "1.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "be4d6b5f19ff7664e8c98d03e2139cb510db9b0a60b55f8e8709b689d939b6bc"
dependencies = [
"serde",
"serde_json",
]
[[package]]
name = "unicode-ident"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
[[package]]
name = "walkdir"
version = "2.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d71d857dc86794ca4c280d616f7da00d2dbfd8cd788846559a6813e6aa4b54ee"
dependencies = [
"same-file",
"winapi-util",
]
[[package]]
name = "wasm-bindgen"
version = "0.2.87"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7706a72ab36d8cb1f80ffbf0e071533974a60d0a308d01a5d0375bf60499a342"
dependencies = [
"cfg-if",
"wasm-bindgen-macro",
]
[[package]]
name = "wasm-bindgen-backend"
version = "0.2.87"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5ef2b6d3c510e9625e5fe6f509ab07d66a760f0885d858736483c32ed7809abd"
dependencies = [
"bumpalo",
"log",
"once_cell",
"proc-macro2",
"quote",
"syn",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-macro"
version = "0.2.87"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dee495e55982a3bd48105a7b947fd2a9b4a8ae3010041b9e0faab3f9cd028f1d"
dependencies = [
"quote",
"wasm-bindgen-macro-support",
]
[[package]]
name = "wasm-bindgen-macro-support"
version = "0.2.87"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "54681b18a46765f095758388f2d0cf16eb8d4169b639ab575a8f5693af210c7b"
dependencies = [
"proc-macro2",
"quote",
"syn",
"wasm-bindgen-backend",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-shared"
version = "0.2.87"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ca6ad05a4870b2bf5fe995117d3728437bd27d7cd5f06f13c17443ef369775a1"
[[package]]
name = "web-sys"
version = "0.3.64"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b85cbef8c220a6abc02aefd892dfc0fc23afb1c6a426316ec33253a3877249b"
dependencies = [
"js-sys",
"wasm-bindgen",
]
[[package]]
name = "winapi"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-util"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f29e6f9198ba0d26b4c9f07dbe6f9ed633e1f3d5b8b414090084349e46a52596"
dependencies = [
"winapi",
]
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
[[package]]
name = "windows-sys"
version = "0.48.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
dependencies = [
"windows-targets",
]
[[package]]
name = "windows-targets"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
dependencies = [
"windows_aarch64_gnullvm",
"windows_aarch64_msvc",
"windows_i686_gnu",
"windows_i686_msvc",
"windows_x86_64_gnu",
"windows_x86_64_gnullvm",
"windows_x86_64_msvc",
]
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
[[package]]
name = "windows_aarch64_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
[[package]]
name = "windows_i686_gnu"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
[[package]]
name = "windows_i686_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
[[package]]
name = "windows_x86_64_gnu"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
[[package]]
name = "windows_x86_64_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
+43
View File
@@ -0,0 +1,43 @@
# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
#
# When uploading crates to the registry Cargo will automatically
# "normalize" Cargo.toml files for maximal compatibility
# with all versions of Cargo and also rewrite `path` dependencies
# to registry (e.g., crates.io) dependencies.
#
# If you are reading this file be aware that the original Cargo.toml
# will likely look very different (and much more reasonable).
# See Cargo.toml.orig for the original contents.
[package]
edition = "2018"
name = "esaxx-rs"
version = "0.1.10"
authors = ["Nicolas Patry <patry.nicolas@protonmail.com>"]
description = "Wrapping around sentencepiece's esaxxx library."
homepage = "https://github.com/Narsil/esaxx-rs"
documentation = "https://docs.rs/esaxx-rs"
readme = "README.md"
license = "Apache-2.0"
repository = "https://github.com/Narsil/esaxx-rs"
[[example]]
name = "esaxx"
required-features = ["cpp"]
[[bench]]
name = "bench_suffix"
harness = false
[dependencies]
[dev-dependencies.criterion]
version = "0.5"
[build-dependencies.cc]
version = "1.0"
optional = true
[features]
cpp = ["cc"]
default = ["cpp"]
+33
View File
@@ -0,0 +1,33 @@
[package]
name = "esaxx-rs"
version = "0.1.10"
authors = ["Nicolas Patry <patry.nicolas@protonmail.com>"]
edition = "2018"
description = "Wrapping around sentencepiece's esaxxx library."
license = "Apache-2.0"
homepage = "https://github.com/Narsil/esaxx-rs"
documentation = "https://docs.rs/esaxx-rs"
repository = "https://github.com/Narsil/esaxx-rs"
readme = "README.md"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
[build-dependencies]
cc = { version = "1.0", optional = true}
[dev-dependencies]
criterion = "0.5"
[features]
default = ["cpp"]
cpp = ["cc"]
[[bench]]
name = "bench_suffix"
harness = false
[[example]]
name = "esaxx"
required-features = ["cpp"]
+201
View File
@@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
+25
View File
@@ -0,0 +1,25 @@
![](https://github.com/Narsil/esaxx-rs/workflows/build/badge.svg)
# esaxx-rs
This code implements a fast suffix tree / suffix array.
This code is taken from ![sentencepiece](https://github.com/google/sentencepiece)
and to be used by ![hugging face](https://github.com/huggingface/tokenizers/).
Small wrapper around sentencepiece's esaxx suffix array C++ library.
Usage
```rust
let string = "abracadabra";
let suffix = esaxx_rs::suffix(string).unwrap();
let chars: Vec<_> = string.chars().collect();
let mut iter = suffix.iter();
assert_eq!(iter.next().unwrap(), (&chars[..4], 2)); // abra
assert_eq!(iter.next(), Some((&chars[..1], 5))); // a
assert_eq!(iter.next(), Some((&chars[1..4], 2))); // bra
assert_eq!(iter.next(), Some((&chars[2..4], 2))); // ra
assert_eq!(iter.next(), Some((&chars[..0], 11))); // ''
assert_eq!(iter.next(), None);
```
+12
View File
@@ -0,0 +1,12 @@
![](https://github.com/Narsil/esaxx-rs/workflows/build/badge.svg)
# {{crate}}
This code implements a fast suffix tree / suffix array.
This code is taken from ![sentencepiece](https://github.com/google/sentencepiece)
and to be used by ![hugging face](https://github.com/huggingface/tokenizers/).
{{readme}}
+24
View File
@@ -0,0 +1,24 @@
use criterion::{black_box, criterion_group, criterion_main, Criterion};
use esaxx_rs::{suffix, suffix_rs};
fn criterion_benchmark(c: &mut Criterion) {
let string = "Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.".to_string();
c.bench_function("suffix_cpp_short", |b| {
b.iter(|| suffix(black_box(&string)).unwrap())
});
c.bench_function("suffix_rust_short", |b| {
b.iter(|| suffix_rs(black_box(&string)).unwrap())
});
let string = std::fs::read_to_string("data/eighty.txt").unwrap();
c.bench_function("suffix_cpp_long", |b| {
b.iter(|| suffix(black_box(&string)).unwrap())
});
c.bench_function("suffix_rust_long", |b| {
b.iter(|| suffix_rs(black_box(&string)).unwrap())
});
}
criterion_group!(benches, criterion_benchmark);
criterion_main!(benches);
+34
View File
@@ -0,0 +1,34 @@
#[cfg(feature = "cpp")]
#[cfg(not(target_os = "macos"))]
fn main() {
let mut build = cc::Build::new();
build.cpp(true).flag("-std=c++11");
if std::env::var("CARGO_CFG_TARGET_FEATURE")
.unwrap_or_default()
.contains("crt-static")
{
build.static_crt(true);
}
build.file("src/esaxx.cpp").include("src").compile("esaxx");
}
#[cfg(feature = "cpp")]
#[cfg(target_os = "macos")]
fn main() {
let mut build = cc::Build::new();
build.cpp(true).flag("-std=c++11").flag("-stdlib=libc++");
if std::env::var("CARGO_CFG_TARGET_FEATURE")
.unwrap_or_default()
.contains("crt-static")
{
build.static_crt(true);
}
build.file("src/esaxx.cpp").include("src").compile("esaxx");
}
#[cfg(not(feature = "cpp"))]
fn main() {}
+8406
View File
File diff suppressed because it is too large Load Diff
+18
View File
@@ -0,0 +1,18 @@
use esaxx_rs::{suffix, suffix_rs};
use std::env::args;
use std::fs;
fn main() {
// Prints each argument on a separate line
let args: Vec<_> = args().skip(1).collect();
let version = &args[0];
let filename = &args[1];
let string = fs::read_to_string(filename).unwrap();
let (count, version) = if version == "rust" {
(suffix_rs(&string).unwrap().iter().count(), "Rust")
} else {
(suffix(&string).unwrap().iter().count(), "Cpp")
};
println!("Used {} version ! Found {} nodes", version, count);
}
+126
View File
@@ -0,0 +1,126 @@
/*
* esa.hxx
* Copyright (c) 2010 Daisuke Okanohara All Rights Reserved.
*
* Permission is hereby granted, free of charge, to any person
* obtaining a copy of this software and associated documentation
* files (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use,
* copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following
* conditions:
*
* The above copyright notice and this permission notice shall be
* included in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
* OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
* HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
* WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
* OTHER DEALINGS IN THE SOFTWARE.
*/
#ifndef _ESA_HXX
#define _ESA_HXX
#include <vector>
#include <utility>
#include <cassert>
#include "sais.hxx"
namespace esaxx_private {
template<typename string_type, typename sarray_type, typename index_type>
index_type suffixtree(string_type T, sarray_type SA, sarray_type L, sarray_type R, sarray_type D, index_type n){
if (n == 0){
return 0;
}
sarray_type Psi = L;
Psi[SA[0]] = SA[n-1];
for (index_type i = 1; i < n; ++i){
Psi[SA[i]] = SA[i-1];
}
// Compare at most 2n log n charcters. Practically fastest
// "Permuted Longest-Common-Prefix Array", Juha Karkkainen, CPM 09
sarray_type PLCP = R;
index_type h = 0;
for (index_type i = 0; i < n; ++i){
index_type j = Psi[i];
while (i+h < n && j+h < n &&
T[i+h] == T[j+h]){
++h;
}
PLCP[i] = h;
if (h > 0) --h;
}
sarray_type H = L;
for (index_type i = 0; i < n; ++i){
H[i] = PLCP[SA[i]];
}
H[0] = -1;
std::vector<std::pair<index_type, index_type> > S;
S.push_back(std::make_pair((index_type)-1, (index_type)-1));
size_t nodeNum = 0;
for (index_type i = 0; ; ++i){
std::pair<index_type, index_type> cur (i, (i == n) ? -1 : H[i]);
std::pair<index_type, index_type> cand(S.back());
while (cand.second > cur.second){
if (i - cand.first > 1){
L[nodeNum] = cand.first;
R[nodeNum] = i;
D[nodeNum] = cand.second;
++nodeNum;
}
cur.first = cand.first;
S.pop_back();
cand = S.back();
}
if (cand.second < cur.second){
S.push_back(cur);
}
if (i == n) break;
S.push_back(std::make_pair(i, n - SA[i] + 1));
}
return nodeNum;
}
}
/**
* @brief Build an enhanced suffix array of a given string in linear time
* For an input text T, esaxx() builds an enhancd suffix array in linear time.
* i-th internal node is represented as a triple (L[i], R[i], D[i]);
* L[i] and R[i] is the left/right boundary of the suffix array as SA[L[i]....R[i]-1]
* D[i] is the depth of the internal node
* The number of internal node is at most N-1 and return the actual number by
* @param T[0...n-1] The input string. (random access iterator)
* @param SA[0...n-1] The output suffix array (random access iterator)
* @param L[0...n-1] The output left boundary of internal node (random access iterator)
* @param R[0...n-1] The output right boundary of internal node (random access iterator)
* @param D[0...n-1] The output depth of internal node (random access iterator)
* @param n The length of the input string
* @param k The alphabet size
* @pram nodeNum The output the number of internal node
* @return 0 if succeded, -1 or -2 otherwise
*/
template<typename string_type, typename sarray_type, typename index_type>
int esaxx(string_type T, sarray_type SA, sarray_type L, sarray_type R, sarray_type D,
index_type n, index_type k, index_type& nodeNum) {
if ((n < 0) || (k <= 0)) return -1;
int err = saisxx(T, SA, n, k);
if (err != 0){
return err;
}
nodeNum = esaxx_private::suffixtree(T, SA, L, R, D, n);
return 0;
}
#endif // _ESA_HXX
+89
View File
@@ -0,0 +1,89 @@
use crate::sais::saisxx;
use crate::types::{SArray, StringT, SuffixError};
use std::convert::TryInto;
fn suffixtree(
string: &StringT,
suffix_array: &mut SArray,
left: &mut SArray,
right: &mut SArray,
depth: &mut SArray,
n: usize,
) -> usize {
if n == 0 {
return 0;
}
// Psi = l
left[suffix_array[0]] = suffix_array[n - 1];
for i in 1..n {
left[suffix_array[i]] = suffix_array[i - 1];
}
// Compare at most 2n log n charcters. Practically fastest
// "Permuted Longest-Common-Prefix Array", Juha Karkkainen, CPM 09
// PLCP = r
let mut h = 0;
for i in 0..n {
let j = left[i];
while i + h < n && j + h < n && string[i + h] == string[j + h] {
h += 1;
}
right[i] = h;
h = h.saturating_sub(1);
}
// H = l
for i in 0..n {
left[i] = right[suffix_array[i]];
}
// TODO XXX: i32 necessary
// l[0] = -1;
let mut s: Vec<(i32, i32)> = vec![(-1, -1)];
let mut node_num = 0;
let mut i: usize = 0;
loop {
let mut cur: (i32, i32) = (i as i32, if i == n { -1 } else { left[i] as i32 });
let mut cand = s[s.len() - 1];
while cand.1 > cur.1 {
if (i as i32) - cand.0 > 1 {
left[node_num] = cand.0.try_into().unwrap();
right[node_num] = i;
depth[node_num] = cand.1.try_into().unwrap();
node_num += 1;
if node_num >= n {
break;
}
}
cur.0 = cand.0;
s.pop();
cand = s[s.len() - 1];
}
if cand.1 < cur.1 {
s.push(cur);
}
if i == n {
break;
}
s.push((
i.try_into().unwrap(),
(n - suffix_array[i] + 1).try_into().unwrap(),
));
i += 1;
}
node_num
}
pub(crate) fn esaxx_rs(
string: &StringT,
suffix_array: &mut SArray,
left: &mut SArray,
right: &mut SArray,
depth: &mut SArray,
k: usize,
) -> Result<usize, SuffixError> {
let n = string.len();
saisxx(string, suffix_array, n, k)?;
let node_num = suffixtree(string, suffix_array, left, right, depth, n);
Ok(node_num)
}
+633
View File
@@ -0,0 +1,633 @@
//
// /*
// * sais.hxx for sais-lite
// * Copyright (c) 2008-2009 Yuta Mori All Rights Reserved.
// *
// * Permission is hereby granted, free of charge, to any person
// * obtaining a copy of this software and associated documentation
// * files (the "Software"), to deal in the Software without
// * restriction, including without limitation the rights to use,
// * copy, modify, merge, publish, distribute, sublicense, and/or sell
// * copies of the Software, and to permit persons to whom the
// * Software is furnished to do so, subject to the following
// * conditions:
// *
// * The above copyright notice and this permission notice shall be
// * included in all copies or substantial portions of the Software.
// *
// * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
// * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
// * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
// * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
// * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
// * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
// * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
// * OTHER DEALINGS IN THE SOFTWARE.
// */
//
// #ifndef _SAIS_HXX
// #define _SAIS_HXX 1
// #ifdef __cplusplus
//
// #ifdef __INTEL_COMPILER
// #pragma warning(disable : 383 981 1418)
// // for icc 64-bit
// //#define __builtin_vsnprintf(a, b, c, d) __builtin_vsnprintf(a, b, c, (char *)d)
// #endif
//
// #include <iterator>
// #ifdef _OPENMP
// # include <omp.h>
// #endif
//
// namespace saisxx_private {
//
// /* find the start or end of each bucket */
// template<typename string_type, typename bucket_type, typename index_type>
// void
// getCounts(const string_type T, bucket_type C, index_type n, index_type k) {
// #ifdef _OPENMP
// bucket_type D;
// index_type i, j, p, sum, first, last;
// int thnum, maxthreads = omp_get_max_threads();
// #pragma omp parallel default(shared) private(D, i, thnum, first, last)
// {
// thnum = omp_get_thread_num();
// D = C + thnum * k;
// first = n / maxthreads * thnum;
// last = (thnum < (maxthreads - 1)) ? n / maxthreads * (thnum + 1) : n;
// for(i = 0; i < k; ++i) { D[i] = 0; }
// for(i = first; i < last; ++i) { ++D[T[i]]; }
// }
// if(1 < maxthreads) {
// #pragma omp parallel for default(shared) private(i, j, p, sum)
// for(i = 0; i < k; ++i) {
// for(j = 1, p = i + k, sum = C[i]; j < maxthreads; ++j, p += k) {
// sum += C[p];
// }
// C[i] = sum;
// }
// }
// #else
// index_type i;
// for(i = 0; i < k; ++i) { C[i] = 0; }
// for(i = 0; i < n; ++i) { ++C[T[i]]; }
// #endif
// }
// template<typename bucket_type, typename index_type>
// void
// getBuckets(const bucket_type C, bucket_type B, index_type k, bool end) {
// index_type i, sum = 0;
// if(end) { for(i = 0; i < k; ++i) { sum += C[i]; B[i] = sum; } }
// else { for(i = 0; i < k; ++i) { sum += C[i]; B[i] = sum - C[i]; } }
// }
//
// /* compute SA and BWT */
// template<typename string_type, typename sarray_type,
// typename bucket_type, typename index_type>
// void
// induceSA(string_type T, sarray_type SA, bucket_type C, bucket_type B,
// index_type n, index_type k) {
// typedef typename std::iterator_traits<string_type>::value_type char_type;
// sarray_type b;
// index_type i, j;
// char_type c0, c1;
// /* compute SAl */
// if(C == B) { getCounts(T, C, n, k); }
// getBuckets(C, B, k, false); /* find starts of buckets */
// b = SA + B[c1 = T[j = n - 1]];
// *b++ = ((0 < j) && (T[j - 1] < c1)) ? ~j : j;
// for(i = 0; i < n; ++i) {
// j = SA[i], SA[i] = ~j;
// if(0 < j) {
// if((c0 = T[--j]) != c1) { B[c1] = b - SA; b = SA + B[c1 = c0]; }
// *b++ = ((0 < j) && (T[j - 1] < c1)) ? ~j : j;
// }
// }
// /* compute SAs */
// if(C == B) { getCounts(T, C, n, k); }
// getBuckets(C, B, k, true); /* find ends of buckets */
// for(i = n - 1, b = SA + B[c1 = 0]; 0 <= i; --i) {
// if(0 < (j = SA[i])) {
// if((c0 = T[--j]) != c1) { B[c1] = b - SA; b = SA + B[c1 = c0]; }
// *--b = ((j == 0) || (T[j - 1] > c1)) ? ~j : j;
// } else {
// SA[i] = ~j;
// }
// }
// }
// template<typename string_type, typename sarray_type,
// typename bucket_type, typename index_type>
// int
// computeBWT(string_type T, sarray_type SA, bucket_type C, bucket_type B,
// index_type n, index_type k) {
// typedef typename std::iterator_traits<string_type>::value_type char_type;
// sarray_type b;
// index_type i, j, pidx = -1;
// char_type c0, c1;
// /* compute SAl */
// if(C == B) { getCounts(T, C, n, k); }
// getBuckets(C, B, k, false); /* find starts of buckets */
// b = SA + B[c1 = T[j = n - 1]];
// *b++ = ((0 < j) && (T[j - 1] < c1)) ? ~j : j;
// for(i = 0; i < n; ++i) {
// if(0 < (j = SA[i])) {
// SA[i] = ~(c0 = T[--j]);
// if(c0 != c1) { B[c1] = b - SA; b = SA + B[c1 = c0]; }
// *b++ = ((0 < j) && (T[j - 1] < c1)) ? ~j : j;
// } else if(j != 0) {
// SA[i] = ~j;
// }
// }
// /* compute SAs */
// if(C == B) { getCounts(T, C, n, k); }
// getBuckets(C, B, k, true); /* find ends of buckets */
// for(i = n - 1, b = SA + B[c1 = 0]; 0 <= i; --i) {
// if(0 < (j = SA[i])) {
// SA[i] = (c0 = T[--j]);
// if(c0 != c1) { B[c1] = b - SA; b = SA + B[c1 = c0]; }
// *--b = ((0 < j) && (T[j - 1] > c1)) ? ~((index_type)T[j - 1]) : j;
// } else if(j != 0) {
// SA[i] = ~j;
// } else {
// pidx = i;
// }
// }
// return pidx;
// }
//
// /* find the suffix array SA of T[0..n-1] in {0..k}^n
// use a working space (excluding s and SA) of at most 2n+O(1) for a constant alphabet */
// template<typename string_type, typename sarray_type, typename index_type>
// int
// suffixsort(string_type T, sarray_type SA,
// index_type fs, index_type n, index_type k,
// bool isbwt) {
// typedef typename std::iterator_traits<string_type>::value_type char_type;
// sarray_type RA;
// index_type i, j, m, p, q, plen, qlen, name, pidx = 0;
// bool diff;
// int c;
// #ifdef _OPENMP
// int maxthreads = omp_get_max_threads();
// #else
// # define maxthreads 1
// #endif
// char_type c0, c1;
//
// /* stage 1: reduce the problem by at least 1/2
// sort all the S-substrings */
// if(fs < (maxthreads * k)) {
// index_type *C, *B;
// if((C = new index_type[maxthreads * k]) == 0) { return -2; }
// B = (1 < maxthreads) ? C + k : C;
// getCounts(T, C, n, k); getBuckets(C, B, k, true); /* find ends of buckets */
// #ifdef _OPENMP
// #pragma omp parallel for default(shared) private(i)
// #endif
// for(i = 0; i < n; ++i) { SA[i] = 0; }
// for(i = n - 2, c = 0, c1 = T[n - 1]; 0 <= i; --i, c1 = c0) {
// if((c0 = T[i]) < (c1 + c)) { c = 1; }
// else if(c != 0) { SA[--B[c1]] = i + 1, c = 0; }
// }
// induceSA(T, SA, C, B, n, k);
// delete [] C;
// } else {
// sarray_type C, B;
// C = SA + n;
// B = ((1 < maxthreads) || (k <= (fs - k))) ? C + k : C;
// getCounts(T, C, n, k); getBuckets(C, B, k, true); /* find ends of buckets */
// #ifdef _OPENMP
// #pragma omp parallel for default(shared) private(i)
// #endif
// for(i = 0; i < n; ++i) { SA[i] = 0; }
// for(i = n - 2, c = 0, c1 = T[n - 1]; 0 <= i; --i, c1 = c0) {
// if((c0 = T[i]) < (c1 + c)) { c = 1; }
// else if(c != 0) { SA[--B[c1]] = i + 1, c = 0; }
// }
// induceSA(T, SA, C, B, n, k);
// }
//
// /* compact all the sorted substrings into the first m items of SA
// 2*m must be not larger than n (proveable) */
// #ifdef _OPENMP
// #pragma omp parallel for default(shared) private(i, j, p, c0, c1)
// for(i = 0; i < n; ++i) {
// p = SA[i];
// if((0 < p) && (T[p - 1] > (c0 = T[p]))) {
// for(j = p + 1; (j < n) && (c0 == (c1 = T[j])); ++j) { }
// if((j < n) && (c0 < c1)) { SA[i] = ~p; }
// }
// }
// for(i = 0, m = 0; i < n; ++i) { if((p = SA[i]) < 0) { SA[m++] = ~p; } }
// #else
// for(i = 0, m = 0; i < n; ++i) {
// p = SA[i];
// if((0 < p) && (T[p - 1] > (c0 = T[p]))) {
// for(j = p + 1; (j < n) && (c0 == (c1 = T[j])); ++j) { }
// if((j < n) && (c0 < c1)) { SA[m++] = p; }
// }
// }
// #endif
// j = m + (n >> 1);
// #ifdef _OPENMP
// #pragma omp parallel for default(shared) private(i)
// #endif
// for(i = m; i < j; ++i) { SA[i] = 0; } /* init the name array buffer */
// /* store the length of all substrings */
// for(i = n - 2, j = n, c = 0, c1 = T[n - 1]; 0 <= i; --i, c1 = c0) {
// if((c0 = T[i]) < (c1 + c)) { c = 1; }
// else if(c != 0) { SA[m + ((i + 1) >> 1)] = j - i - 1; j = i + 1; c = 0; }
// }
// /* find the lexicographic names of all substrings */
// for(i = 0, name = 0, q = n, qlen = 0; i < m; ++i) {
// p = SA[i], plen = SA[m + (p >> 1)], diff = true;
// if(plen == qlen) {
// for(j = 0; (j < plen) && (T[p + j] == T[q + j]); ++j) { }
// if(j == plen) { diff = false; }
// }
// if(diff != false) { ++name, q = p, qlen = plen; }
// SA[m + (p >> 1)] = name;
// }
//
// /* stage 2: solve the reduced problem
// recurse if names are not yet unique */
// if(name < m) {
// RA = SA + n + fs - m;
// for(i = m + (n >> 1) - 1, j = m - 1; m <= i; --i) {
// if(SA[i] != 0) { RA[j--] = SA[i] - 1; }
// }
// if(suffixsort(RA, SA, fs + n - m * 2, m, name, false) != 0) { return -2; }
// for(i = n - 2, j = m - 1, c = 0, c1 = T[n - 1]; 0 <= i; --i, c1 = c0) {
// if((c0 = T[i]) < (c1 + c)) { c = 1; }
// else if(c != 0) { RA[j--] = i + 1, c = 0; } /* get p1 */
// }
// #ifdef _OPENMP
// #pragma omp parallel for default(shared) private(i)
// #endif
// for(i = 0; i < m; ++i) { SA[i] = RA[SA[i]]; } /* get index in s */
// }
//
// /* stage 3: induce the result for the original problem */
// if(fs < (maxthreads * k)) {
// index_type *B, *C;
// if((C = new index_type[maxthreads * k]) == 0) { return -2; }
// B = (1 < maxthreads) ? C + k : C;
// /* put all left-most S characters into their buckets */
// getCounts(T, C, n, k); getBuckets(C, B, k, true); /* find ends of buckets */
// #ifdef _OPENMP
// #pragma omp parallel for default(shared) private(i)
// #endif
// for(i = m; i < n; ++i) { SA[i] = 0; } /* init SA[m..n-1] */
// for(i = m - 1; 0 <= i; --i) {
// j = SA[i], SA[i] = 0;
// SA[--B[T[j]]] = j;
// }
// if(isbwt == false) { induceSA(T, SA, C, B, n, k); }
// else { pidx = computeBWT(T, SA, C, B, n, k); }
// delete [] C;
// } else {
// sarray_type C, B;
// C = SA + n;
// B = ((1 < maxthreads) || (k <= (fs - k))) ? C + k : C;
// /* put all left-most S characters into their buckets */
// getCounts(T, C, n, k); getBuckets(C, B, k, true); /* find ends of buckets */
// #ifdef _OPENMP
// #pragma omp parallel for default(shared) private(i)
// #endif
// for(i = m; i < n; ++i) { SA[i] = 0; } /* init SA[m..n-1] */
// for(i = m - 1; 0 <= i; --i) {
// j = SA[i], SA[i] = 0;
// SA[--B[T[j]]] = j;
// }
// if(isbwt == false) { induceSA(T, SA, C, B, n, k); }
// else { pidx = computeBWT(T, SA, C, B, n, k); }
// }
//
// return pidx;
// #ifndef _OPENMP
// # undef maxthreads
// #endif
// }
//
// } /* namespace saisxx_private */
//
//
// /**
// * @brief Constructs the suffix array of a given string in linear time.
// * @param T[0..n-1] The input string. (random access iterator)
// * @param SA[0..n-1] The output array of suffixes. (random access iterator)
// * @param n The length of the given string.
// * @param k The alphabet size.
// * @return 0 if no error occurred, -1 or -2 otherwise.
// */
// template<typename string_type, typename sarray_type, typename index_type>
// int
// saisxx(string_type T, sarray_type SA, index_type n, index_type k = 256) {
// int err;
// if((n < 0) || (k <= 0)) { return -1; }
// if(n <= 1) { if(n == 1) { SA[0] = 0; } return 0; }
// try { err = saisxx_private::suffixsort(T, SA, 0U, n, k, false); }
// catch(...) { err = -2; }
// return err;
// }
//
// /**
// * @brief Constructs the burrows-wheeler transformed string of a given string in linear time.
// * @param T[0..n-1] The input string. (random access iterator)
// * @param U[0..n-1] The output string. (random access iterator)
// * @param A[0..n-1] The temporary array. (random access iterator)
// * @param n The length of the given string.
// * @param k The alphabet size.
// * @return The primary index if no error occurred, -1 or -2 otherwise.
// */
// template<typename string_type, typename sarray_type, typename index_type>
// index_type
// saisxx_bwt(string_type T, string_type U, sarray_type A, index_type n, index_type k = 256) {
// typedef typename std::iterator_traits<string_type>::value_type char_type;
// index_type i, pidx;
// if((n < 0) || (k <= 0)) { return -1; }
// if(n <= 1) { if(n == 1) { U[0] = T[0]; } return n; }
// try {
// pidx = saisxx_private::suffixsort(T, A, 0, n, k, true);
// if(0 <= pidx) {
// U[0] = T[n - 1];
// for(i = 0; i < pidx; ++i) { U[i + 1] = (char_type)A[i]; }
// for(i += 1; i < n; ++i) { U[i] = (char_type)A[i]; }
// pidx += 1;
// }
// } catch(...) { pidx = -2; }
// return pidx;
// }
//
//
// #endif /* __cplusplus */
// #endif /* _SAIS_HXX */
// /*
// * esa.hxx
// * Copyright (c) 2010 Daisuke Okanohara All Rights Reserved.
// *
// * Permission is hereby granted, free of charge, to any person
// * obtaining a copy of this software and associated documentation
// * files (the "Software"), to deal in the Software without
// * restriction, including without limitation the rights to use,
// * copy, modify, merge, publish, distribute, sublicense, and/or sell
// * copies of the Software, and to permit persons to whom the
// * Software is furnished to do so, subject to the following
// * conditions:
// *
// * The above copyright notice and this permission notice shall be
// * included in all copies or substantial portions of the Software.
// *
// * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
// * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
// * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
// * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
// * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
// * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
// * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
// * OTHER DEALINGS IN THE SOFTWARE.
// */
//
// #ifndef _ESA_HXX
// #define _ESA_HXX
//
// #include <vector>
// #include <utility>
// #include <cassert>
// #include "sais.hxx"
//
// namespace esaxx_private {
// template<typename string_type, typename sarray_type, typename index_type>
// index_type suffixtree(string_type T, sarray_type SA, sarray_type L, sarray_type R, sarray_type D, index_type n){
// if (n == 0){
// return 0;
// }
// sarray_type Psi = L;
// Psi[SA[0]] = SA[n-1];
// for (index_type i = 1; i < n; ++i){
// Psi[SA[i]] = SA[i-1];
// }
//
// // Compare at most 2n log n charcters. Practically fastest
// // "Permuted Longest-Common-Prefix Array", Juha Karkkainen, CPM 09
// sarray_type PLCP = R;
// index_type h = 0;
// for (index_type i = 0; i < n; ++i){
// index_type j = Psi[i];
// while (i+h < n && j+h < n &&
// T[i+h] == T[j+h]){
// ++h;
// }
// PLCP[i] = h;
// if (h > 0) --h;
// }
//
// sarray_type H = L;
// for (index_type i = 0; i < n; ++i){
// H[i] = PLCP[SA[i]];
// }
// H[0] = -1;
//
// std::vector<std::pair<index_type, index_type> > S;
// S.push_back(std::make_pair((index_type)-1, (index_type)-1));
// size_t nodeNum = 0;
// for (index_type i = 0; ; ++i){
// std::pair<index_type, index_type> cur (i, (i == n) ? -1 : H[i]);
// std::pair<index_type, index_type> cand(S.back());
// while (cand.second > cur.second){
// if (i - cand.first > 1){
// L[nodeNum] = cand.first;
// R[nodeNum] = i;
// D[nodeNum] = cand.second;
// ++nodeNum;
// }
// cur.first = cand.first;
// S.pop_back();
// cand = S.back();
// }
// if (cand.second < cur.second){
// S.push_back(cur);
// }
// if (i == n) break;
// S.push_back(std::make_pair(i, n - SA[i] + 1));
// }
// return nodeNum;
// }
// }
//
// /**
// * @brief Build an enhanced suffix array of a given string in linear time
// * For an input text T, esaxx() builds an enhancd suffix array in linear time.
// * i-th internal node is represented as a triple (L[i], R[i], D[i]);
// * L[i] and R[i] is the left/right boundary of the suffix array as SA[L[i]....R[i]-1]
// * D[i] is the depth of the internal node
// * The number of internal node is at most N-1 and return the actual number by
// * @param T[0...n-1] The input string. (random access iterator)
// * @param SA[0...n-1] The output suffix array (random access iterator)
// * @param L[0...n-1] The output left boundary of internal node (random access iterator)
// * @param R[0...n-1] The output right boundary of internal node (random access iterator)
// * @param D[0...n-1] The output depth of internal node (random access iterator)
// * @param n The length of the input string
// * @param k The alphabet size
// * @pram nodeNum The output the number of internal node
// * @return 0 if succeded, -1 or -2 otherwise
// */
//
// template<typename string_type, typename sarray_type, typename index_type>
// int esaxx(string_type T, sarray_type SA, sarray_type L, sarray_type R, sarray_type D,
// index_type n, index_type k, index_type& nodeNum) {
// if ((n < 0) || (k <= 0)) return -1;
// int err = saisxx(T, SA, n, k);
// if (err != 0){
// return err;
// }
// nodeNum = esaxx_private::suffixtree(T, SA, L, R, D, n);
// return 0;
// }
//
//
// #endif // _ESA_HXX
// /*
// * esa.hxx
// * Copyright (c) 2010 Daisuke Okanohara All Rights Reserved.
// *
// * Permission is hereby granted, free of charge, to any person
// * obtaining a copy of this software and associated documentation
// * files (the "Software"), to deal in the Software without
// * restriction, including without limitation the rights to use,
// * copy, modify, merge, publish, distribute, sublicense, and/or sell
// * copies of the Software, and to permit persons to whom the
// * Software is furnished to do so, subject to the following
// * conditions:
// *
// * The above copyright notice and this permission notice shall be
// * included in all copies or substantial portions of the Software.
// *
// * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
// * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
// * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
// * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
// * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
// * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
// * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
// * OTHER DEALINGS IN THE SOFTWARE.
// */
//
// #ifndef _ESA_HXX
// #define _ESA_HXX
//
// #include <vector>
// #include <utility>
// #include <cassert>
// #include "sais.hxx"
//
// namespace esaxx_private {
// template<typename string_type, typename sarray_type, typename index_type>
// index_type suffixtree(string_type T, sarray_type SA, sarray_type L, sarray_type R, sarray_type D, index_type n){
// if (n == 0){
// return 0;
// }
// sarray_type Psi = L;
// Psi[SA[0]] = SA[n-1];
// for (index_type i = 1; i < n; ++i){
// Psi[SA[i]] = SA[i-1];
// }
//
// // Compare at most 2n log n charcters. Practically fastest
// // "Permuted Longest-Common-Prefix Array", Juha Karkkainen, CPM 09
// sarray_type PLCP = R;
// index_type h = 0;
// for (index_type i = 0; i < n; ++i){
// index_type j = Psi[i];
// while (i+h < n && j+h < n &&
// T[i+h] == T[j+h]){
// ++h;
// }
// PLCP[i] = h;
// if (h > 0) --h;
// }
//
// sarray_type H = L;
// for (index_type i = 0; i < n; ++i){
// H[i] = PLCP[SA[i]];
// }
// H[0] = -1;
//
// std::vector<std::pair<index_type, index_type> > S;
// S.push_back(std::make_pair((index_type)-1, (index_type)-1));
// size_t nodeNum = 0;
// for (index_type i = 0; ; ++i){
// std::pair<index_type, index_type> cur (i, (i == n) ? -1 : H[i]);
// std::pair<index_type, index_type> cand(S.back());
// while (cand.second > cur.second){
// if (i - cand.first > 1){
// L[nodeNum] = cand.first;
// R[nodeNum] = i;
// D[nodeNum] = cand.second;
// ++nodeNum;
// }
// cur.first = cand.first;
// S.pop_back();
// cand = S.back();
// }
// if (cand.second < cur.second){
// S.push_back(cur);
// }
// if (i == n) break;
// S.push_back(std::make_pair(i, n - SA[i] + 1));
// }
// return nodeNum;
// }
// }
//
// /**
// * @brief Build an enhanced suffix array of a given string in linear time
// * For an input text T, esaxx() builds an enhancd suffix array in linear time.
// * i-th internal node is represented as a triple (L[i], R[i], D[i]);
// * L[i] and R[i] is the left/right boundary of the suffix array as SA[L[i]....R[i]-1]
// * D[i] is the depth of the internal node
// * The number of internal node is at most N-1 and return the actual number by
// * @param T[0...n-1] The input string. (random access iterator)
// * @param SA[0...n-1] The output suffix array (random access iterator)
// * @param L[0...n-1] The output left boundary of internal node (random access iterator)
// * @param R[0...n-1] The output right boundary of internal node (random access iterator)
// * @param D[0...n-1] The output depth of internal node (random access iterator)
// * @param n The length of the input string
// * @param k The alphabet size
// * @pram nodeNum The output the number of internal node
// * @return 0 if succeded, -1 or -2 otherwise
// */
//
// template<typename string_type, typename sarray_type, typename index_type>
// int esaxx(string_type T, sarray_type SA, sarray_type L, sarray_type R, sarray_type D,
// index_type n, index_type k, index_type& nodeNum) {
// if ((n < 0) || (k <= 0)) return -1;
// std::count<<"Here"<<std::endl;
// int err = saisxx(T, SA, n, k);
// if (err != 0){
// return err;
// }
// std::cout<<"suffixtree"<<std::endl;
// nodeNum = esaxx_private::suffixtree(T, SA, L, R, D, n);
// std::count<<"ok"<<std::endl;
// return 0;
// }
//
//
// #endif // _ESA_HXX
#include <cstdint>
#include "esa.hxx"
extern "C"{
int esaxx_int32(char32_t* T, int32_t* SA, int32_t* L, int32_t* R, int32_t* D,
int32_t n, int32_t k, int32_t &nodeNum) {
return esaxx(T, SA, L, R, D, n, k, nodeNum);
}
}
+383
View File
@@ -0,0 +1,383 @@
//! Small wrapper around sentencepiece's esaxx suffix array C++ library.
//! Usage
//!
//! ```rust
//! #[cfg(feature="cpp")]
//! {
//! let string = "abracadabra";
//! let suffix = esaxx_rs::suffix(string).unwrap();
//! let chars: Vec<_> = string.chars().collect();
//! let mut iter = suffix.iter();
//! assert_eq!(iter.next().unwrap(), (&chars[..4], 2)); // abra
//! assert_eq!(iter.next(), Some((&chars[..1], 5))); // a
//! assert_eq!(iter.next(), Some((&chars[1..4], 2))); // bra
//! assert_eq!(iter.next(), Some((&chars[2..4], 2))); // ra
//! assert_eq!(iter.next(), Some((&chars[..0], 11))); // ''
//! assert_eq!(iter.next(), None);
//! }
//! ```
//!
//! The previous version uses unsafe optimized c++ code.
//! There exists another implementation a bit slower (~2x slower) that uses
//! safe rust. It's a bit slower because it uses usize (mostly 64bit) instead of i32 (32bit).
//! But it does seems to fix a few OOB issues in the cpp version
//! (which never seemed to cause real problems in tests but still.)
//!
//! ```rust
//! let string = "abracadabra";
//! let suffix = esaxx_rs::suffix_rs(string).unwrap();
//! let chars: Vec<_> = string.chars().collect();
//! let mut iter = suffix.iter();
//! assert_eq!(iter.next().unwrap(), (&chars[..4], 2)); // abra
//! assert_eq!(iter.next(), Some((&chars[..1], 5))); // a
//! assert_eq!(iter.next(), Some((&chars[1..4], 2))); // bra
//! assert_eq!(iter.next(), Some((&chars[2..4], 2))); // ra
//! assert_eq!(iter.next(), Some((&chars[..0], 11))); // ''
//! assert_eq!(iter.next(), None);
//! ```
use std::convert::TryInto;
mod esa;
mod sais;
mod types;
use esa::esaxx_rs;
use types::SuffixError;
#[cfg(feature = "cc")]
extern "C" {
fn esaxx_int32(
// This is char32
T: *const u32,
SA: *mut i32,
L: *mut i32,
R: *mut i32,
D: *mut i32,
n: u32,
k: u32,
nodeNum: &mut u32,
) -> i32;
}
#[cfg(feature = "cc")]
fn esaxx(
chars: &[char],
sa: &mut [i32],
l: &mut [i32],
r: &mut [i32],
d: &mut [i32],
alphabet_size: u32,
node_num: &mut u32,
) -> Result<(), SuffixError> {
let n = chars.len();
if sa.len() != n || l.len() != n || r.len() != n || d.len() != n {
return Err(SuffixError::InvalidLength);
}
unsafe {
let err = esaxx_int32(
chars.as_ptr() as *const u32,
sa.as_mut_ptr(),
l.as_mut_ptr(),
r.as_mut_ptr(),
d.as_mut_ptr(),
n.try_into().unwrap(),
alphabet_size,
node_num,
);
if err != 0 {
return Err(SuffixError::Internal);
}
}
Ok(())
}
pub struct SuffixIterator<'a, T> {
i: usize,
suffix: &'a Suffix<T>,
}
pub struct Suffix<T> {
chars: Vec<char>,
sa: Vec<T>,
l: Vec<T>,
r: Vec<T>,
d: Vec<T>,
node_num: usize,
}
/// Creates the suffix array and provides an iterator over its items (Rust version)
/// See [suffix](fn.suffix.html)
pub fn suffix_rs(string: &str) -> Result<Suffix<usize>, SuffixError> {
let chars: Vec<_> = string.chars().collect();
let n = chars.len();
let mut sa = vec![0; n];
let mut l = vec![0; n];
let mut r = vec![0; n];
let mut d = vec![0; n];
let alphabet_size = 0x110000; // All UCS4 range.
let node_num = esaxx_rs(
&chars.iter().map(|c| *c as u32).collect::<Vec<_>>(),
&mut sa,
&mut l,
&mut r,
&mut d,
alphabet_size,
)?;
Ok(Suffix {
chars,
sa,
l,
r,
d,
node_num,
})
}
/// Creates the suffix array and provides an iterator over its items (c++ unsafe version)
///
/// Gives you an iterator over the suffixes of the input array and their count within
/// the input srtring.
/// ```rust
/// let string = "abracadabra";
/// let suffix = esaxx_rs::suffix(string).unwrap();
/// let chars: Vec<_> = string.chars().collect();
/// let mut iter = suffix.iter();
/// assert_eq!(iter.next().unwrap(), (&chars[..4], 2)); // abra
/// assert_eq!(iter.next(), Some((&chars[..1], 5))); // a
/// assert_eq!(iter.next(), Some((&chars[1..4], 2))); // bra
/// assert_eq!(iter.next(), Some((&chars[2..4], 2))); // ra
/// assert_eq!(iter.next(), Some((&chars[..0], 11))); // ''
/// assert_eq!(iter.next(), None);
/// ```
#[cfg(feature = "cpp")]
pub fn suffix(string: &str) -> Result<Suffix<i32>, SuffixError> {
let chars: Vec<_> = string.chars().collect();
let n = chars.len();
let mut sa = vec![0; n];
let mut l = vec![0; n];
let mut r = vec![0; n];
let mut d = vec![0; n];
let mut node_num = 0;
let alphabet_size = 0x110000; // All UCS4 range.
esaxx(
&chars,
&mut sa,
&mut l,
&mut r,
&mut d,
alphabet_size,
&mut node_num,
)?;
Ok(Suffix {
chars,
sa,
l,
r,
d,
node_num: node_num.try_into()?,
})
}
impl<T> Suffix<T> {
pub fn iter(&self) -> SuffixIterator<'_, T> {
SuffixIterator { i: 0, suffix: self }
}
}
impl<'a> Iterator for SuffixIterator<'a, i32> {
type Item = (&'a [char], u32);
fn next(&mut self) -> Option<Self::Item> {
let index = self.i;
if index == self.suffix.node_num {
None
} else {
let left: usize = self.suffix.l[index].try_into().ok()?;
let offset: usize = self.suffix.sa[left].try_into().ok()?;
let len: usize = self.suffix.d[index].try_into().ok()?;
let freq: u32 = (self.suffix.r[index] - self.suffix.l[index])
.try_into()
.ok()?;
self.i += 1;
Some((&self.suffix.chars[offset..offset + len], freq))
}
}
}
impl<'a> Iterator for SuffixIterator<'a, usize> {
type Item = (&'a [char], u32);
fn next(&mut self) -> Option<Self::Item> {
let index = self.i;
if index == self.suffix.node_num {
None
} else {
let left: usize = self.suffix.l[index];
let offset: usize = self.suffix.sa[left];
let len: usize = self.suffix.d[index];
let freq: u32 = (self.suffix.r[index] - self.suffix.l[index])
.try_into()
.unwrap();
self.i += 1;
Some((&self.suffix.chars[offset..offset + len], freq))
}
}
}
#[cfg(test)]
#[cfg(feature = "cpp")]
mod cpp_tests {
use super::*;
#[test]
fn test_esaxx() {
let string = "abracadabra".to_string();
let chars: Vec<_> = string.chars().collect();
let n = chars.len();
let mut sa = vec![0; n];
let mut l = vec![0; n];
let mut r = vec![0; n];
let mut d = vec![0; n];
let mut node_num = 0;
let alphabet_size = 0x110000; // All UCS4 range.
esaxx(
&chars,
&mut sa,
&mut l,
&mut r,
&mut d,
alphabet_size,
&mut node_num,
)
.unwrap();
assert_eq!(node_num, 5);
assert_eq!(sa, vec![10, 7, 0, 3, 5, 8, 1, 4, 6, 9, 2]);
assert_eq!(l, vec![1, 0, 5, 9, 0, 0, 3, 0, 0, 0, 2]);
assert_eq!(r, vec![3, 5, 7, 11, 11, 1, 0, 1, 0, 0, 0]);
assert_eq!(d, vec![4, 1, 3, 2, 0, 0, 0, 0, 0, 0, 0]);
}
#[test]
fn test_esaxx_long() {
let string = "Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.".to_string();
let chars: Vec<_> = string.chars().collect();
let n = chars.len();
let mut sa = vec![0; n];
let mut l = vec![0; n];
let mut r = vec![0; n];
let mut d = vec![0; n];
let mut node_num = 0;
let alphabet_size = 0x110000; // All UCS4 range.
esaxx(
&chars,
&mut sa,
&mut l,
&mut r,
&mut d,
alphabet_size,
&mut node_num,
)
.unwrap();
assert_eq!(chars.len(), 574);
assert_eq!(node_num, 260);
// assert_eq!(sa, vec![10, 7, 0, 3, 5, 8, 1, 4, 6, 9, 2]);
// assert_eq!(l, vec![1, 0, 5, 9, 0, 0, 3, 0, 0, 0, 2]);
// assert_eq!(r, vec![3, 5, 7, 11, 11, 1, 0, 1, 0, 0, 0]);
// assert_eq!(d, vec![4, 1, 3, 2, 0, 0, 0, 0, 0, 0, 0]);
}
#[test]
fn test_suffix() {
let suffix = suffix("abracadabra").unwrap();
assert_eq!(suffix.node_num, 5);
assert_eq!(suffix.sa, vec![10, 7, 0, 3, 5, 8, 1, 4, 6, 9, 2]);
assert_eq!(suffix.l, vec![1, 0, 5, 9, 0, 0, 3, 0, 0, 0, 2]);
assert_eq!(suffix.r, vec![3, 5, 7, 11, 11, 1, 0, 1, 0, 0, 0]);
assert_eq!(suffix.d, vec![4, 1, 3, 2, 0, 0, 0, 0, 0, 0, 0]);
let mut iter = suffix.iter();
let chars: Vec<_> = "abracadabra".chars().collect();
assert_eq!(iter.next(), Some((&chars[..4], 2))); // abra
assert_eq!(iter.next(), Some((&chars[..1], 5))); // a
assert_eq!(iter.next(), Some((&chars[1..4], 2))); // bra
assert_eq!(iter.next(), Some((&chars[2..4], 2))); // ra
assert_eq!(iter.next(), Some((&chars[..0], 11))); // ''
assert_eq!(iter.next(), None);
}
}
#[cfg(test)]
mod rs_tests {
use super::*;
#[test]
fn test_esaxx_rs() {
let string = "abracadabra".to_string();
let chars: Vec<_> = string.chars().map(|c| c as u32).collect();
let n = chars.len();
let mut sa = vec![0; n];
let mut l = vec![0; n];
let mut r = vec![0; n];
let mut d = vec![0; n];
let alphabet_size = 0x110000; // All UCS4 range.
let node_num = esaxx_rs(&chars, &mut sa, &mut l, &mut r, &mut d, alphabet_size).unwrap();
println!("Node num {}", node_num);
println!("sa {:?}", sa);
println!("l {:?}", l);
println!("r {:?}", r);
println!("d {:?}", d);
assert_eq!(node_num, 5);
assert_eq!(sa, vec![10, 7, 0, 3, 5, 8, 1, 4, 6, 9, 2]);
assert_eq!(l, vec![1, 0, 5, 9, 0, 0, 3, 0, 0, 0, 2]);
assert_eq!(r, vec![3, 5, 7, 11, 11, 1, 0, 1, 0, 0, 0]);
assert_eq!(d, vec![4, 1, 3, 2, 0, 0, 0, 0, 0, 0, 0]);
}
#[test]
fn test_esaxx_rs_long() {
let string = "Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.".to_string();
let chars: Vec<_> = string.chars().map(|c| c as u32).collect();
let n = chars.len();
let mut sa = vec![0; n];
let mut l = vec![0; n];
let mut r = vec![0; n];
let mut d = vec![0; n];
let alphabet_size = 0x110000; // All UCS4 range.
let node_num = esaxx_rs(&chars, &mut sa, &mut l, &mut r, &mut d, alphabet_size).unwrap();
assert_eq!(chars.len(), 574);
assert_eq!(node_num, 260);
// assert_eq!(sa, vec![10, 7, 0, 3, 5, 8, 1, 4, 6, 9, 2]);
// assert_eq!(l, vec![1, 0, 5, 9, 0, 0, 3, 0, 0, 0, 2]);
// assert_eq!(r, vec![3, 5, 7, 11, 11, 1, 0, 1, 0, 0, 0]);
// assert_eq!(d, vec![4, 1, 3, 2, 0, 0, 0, 0, 0, 0, 0]);
}
#[test]
fn test_suffix_rs() {
let suffix = suffix_rs("abracadabra").unwrap();
assert_eq!(suffix.node_num, 5);
assert_eq!(suffix.sa, vec![10, 7, 0, 3, 5, 8, 1, 4, 6, 9, 2]);
assert_eq!(suffix.l, vec![1, 0, 5, 9, 0, 0, 3, 0, 0, 0, 2]);
assert_eq!(suffix.r, vec![3, 5, 7, 11, 11, 1, 0, 1, 0, 0, 0]);
assert_eq!(suffix.d, vec![4, 1, 3, 2, 0, 0, 0, 0, 0, 0, 0]);
let mut iter = suffix.iter();
let chars: Vec<_> = "abracadabra".chars().collect();
assert_eq!(iter.next(), Some((&chars[..4], 2))); // abra
assert_eq!(iter.next(), Some((&chars[..1], 5))); // a
assert_eq!(iter.next(), Some((&chars[1..4], 2))); // bra
assert_eq!(iter.next(), Some((&chars[2..4], 2))); // ra
assert_eq!(iter.next(), Some((&chars[..0], 11))); // ''
assert_eq!(iter.next(), None);
}
#[test]
fn test_out_of_bounds_bug() {
let string = "banana$band$$";
suffix_rs(string).unwrap();
}
}
+377
View File
@@ -0,0 +1,377 @@
/*
* sais.hxx for sais-lite
* Copyright (c) 2008-2009 Yuta Mori All Rights Reserved.
*
* Permission is hereby granted, free of charge, to any person
* obtaining a copy of this software and associated documentation
* files (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use,
* copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following
* conditions:
*
* The above copyright notice and this permission notice shall be
* included in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
* OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
* HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
* WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
* OTHER DEALINGS IN THE SOFTWARE.
*/
#ifndef _SAIS_HXX
#define _SAIS_HXX 1
#ifdef __cplusplus
#ifdef __INTEL_COMPILER
#pragma warning(disable : 383 981 1418)
// for icc 64-bit
//#define __builtin_vsnprintf(a, b, c, d) __builtin_vsnprintf(a, b, c, (char *)d)
#endif
#include <iterator>
#ifdef _OPENMP
# include <omp.h>
#endif
#include <iostream>
int32_t f(const int32_t s){
int a = ((s < 0)?-~s:s);
return a;
}
namespace saisxx_private {
/* find the start or end of each bucket */
template<typename string_type, typename bucket_type, typename index_type>
void
getCounts(const string_type T, bucket_type C, index_type n, index_type k) {
#ifdef _OPENMP
bucket_type D;
index_type i, j, p, sum, first, last;
int thnum, maxthreads = omp_get_max_threads();
#pragma omp parallel default(shared) private(D, i, thnum, first, last)
{
thnum = omp_get_thread_num();
D = C + thnum * k;
first = n / maxthreads * thnum;
last = (thnum < (maxthreads - 1)) ? n / maxthreads * (thnum + 1) : n;
for(i = 0; i < k; ++i) { D[i] = 0; }
for(i = first; i < last; ++i) { ++D[T[i]]; }
}
if(1 < maxthreads) {
#pragma omp parallel for default(shared) private(i, j, p, sum)
for(i = 0; i < k; ++i) {
for(j = 1, p = i + k, sum = C[i]; j < maxthreads; ++j, p += k) {
sum += C[p];
}
C[i] = sum;
}
}
#else
index_type i;
for(i = 0; i < k; ++i) { C[i] = 0; }
for(i = 0; i < n; ++i) { ++C[T[i]]; }
#endif
}
template<typename bucket_type, typename index_type>
void
getBuckets(const bucket_type C, bucket_type B, index_type k, bool end) {
index_type i, sum = 0;
if(end) { for(i = 0; i < k; ++i) { sum += C[i]; B[i] = sum; } }
else { for(i = 0; i < k; ++i) { sum += C[i]; B[i] = sum - C[i]; } }
}
/* compute SA and BWT */
template<typename string_type, typename sarray_type,
typename bucket_type, typename index_type>
void
induceSA(string_type T, sarray_type SA, bucket_type C, bucket_type B,
index_type n, index_type k) {
typedef typename std::iterator_traits<string_type>::value_type char_type;
sarray_type b;
index_type i, j;
char_type c0, c1;
/* compute SAl */
if(C == B) {
getCounts(T, C, n, k); }
getBuckets(C, B, k, false); /* find starts of buckets */
b = SA + B[c1 = T[j = n - 1]];
*b++ = ((0 < j) && (T[j - 1] < c1)) ? ~j : j;
for(i = 0; i < n; ++i) {
j = SA[i], SA[i] = ~j;
if(0 < j) {
if((c0 = T[--j]) != c1) { B[c1] = b - SA; b = SA + B[c1 = c0]; }
*b++ = ((0 < j) && (T[j - 1] < c1)) ? ~j : j;
}
}
/* compute SAs */
if(C == B) { getCounts(T, C, n, k); }
getBuckets(C, B, k, true); /* find ends of buckets */
for(i = n - 1, b = SA + B[c1 = 0]; 0 <= i; --i) {
if(0 < (j = SA[i])) {
if((c0 = T[--j]) != c1) { B[c1] = b - SA; b = SA + B[c1 = c0]; }
*--b = ((j == 0) || (T[j - 1] > c1)) ? ~j : j;
} else {
SA[i] = ~j;
}
}
}
template<typename string_type, typename sarray_type,
typename bucket_type, typename index_type>
int
computeBWT(string_type T, sarray_type SA, bucket_type C, bucket_type B,
index_type n, index_type k) {
typedef typename std::iterator_traits<string_type>::value_type char_type;
sarray_type b;
index_type i, j, pidx = -1;
char_type c0, c1;
/* compute SAl */
if(C == B) { getCounts(T, C, n, k); }
getBuckets(C, B, k, false); /* find starts of buckets */
b = SA + B[c1 = T[j = n - 1]];
*b++ = ((0 < j) && (T[j - 1] < c1)) ? ~j : j;
for(i = 0; i < n; ++i) {
if(0 < (j = SA[i])) {
SA[i] = ~(c0 = T[--j]);
if(c0 != c1) { B[c1] = b - SA; b = SA + B[c1 = c0]; }
*b++ = ((0 < j) && (T[j - 1] < c1)) ? ~j : j;
} else if(j != 0) {
SA[i] = ~j;
}
}
/* compute SAs */
if(C == B) { getCounts(T, C, n, k); }
getBuckets(C, B, k, true); /* find ends of buckets */
for(i = n - 1, b = SA + B[c1 = 0]; 0 <= i; --i) {
if(0 < (j = SA[i])) {
SA[i] = (c0 = T[--j]);
if(c0 != c1) { B[c1] = b - SA; b = SA + B[c1 = c0]; }
*--b = ((0 < j) && (T[j - 1] > c1)) ? ~((index_type)T[j - 1]) : j;
} else if(j != 0) {
SA[i] = ~j;
} else {
pidx = i;
}
}
return pidx;
}
/* find the suffix array SA of T[0..n-1] in {0..k}^n
use a working space (excluding s and SA) of at most 2n+O(1) for a constant alphabet */
template<typename string_type, typename sarray_type, typename index_type>
int
suffixsort(string_type T, sarray_type SA,
index_type fs, index_type n, index_type k,
bool isbwt) {
typedef typename std::iterator_traits<string_type>::value_type char_type;
sarray_type RA;
index_type i, j, m, p, q, plen, qlen, name;
int pidx = 0;
bool diff;
int c;
#ifdef _OPENMP
int maxthreads = omp_get_max_threads();
#else
# define maxthreads 1
#endif
char_type c0, c1;
/* stage 1: reduce the problem by at least 1/2
sort all the S-substrings */
if(fs < (maxthreads * k)) {
index_type *C, *B;
if((C = new index_type[maxthreads * k]) == 0) { return -2; }
B = (1 < maxthreads) ? C + k : C;
getCounts(T, C, n, k); getBuckets(C, B, k, true); /* find ends of buckets */
#ifdef _OPENMP
#pragma omp parallel for default(shared) private(i)
#endif
for(i = 0; i < n; ++i) { SA[i] = 0; }
for(i = n - 2, c = 0, c1 = T[n - 1]; 0 <= i; --i, c1 = c0) {
if((c0 = T[i]) < (c1 + c)) { c = 1; }
else if(c != 0) { SA[--B[c1]] = i + 1, c = 0; }
}
induceSA(T, SA, C, B, n, k);
delete [] C;
} else {
sarray_type C, B;
C = SA + n;
B = ((1 < maxthreads) || (k <= (fs - k))) ? C + k : C;
getCounts(T, C, n, k); getBuckets(C, B, k, true); /* find ends of buckets */
#ifdef _OPENMP
#pragma omp parallel for default(shared) private(i)
#endif
for(i = 0; i < n; ++i) { SA[i] = 0; }
for(i = n - 2, c = 0, c1 = T[n - 1]; 0 <= i; --i, c1 = c0) {
if((c0 = T[i]) < (c1 + c)) { c = 1; }
else if(c != 0) { SA[--B[c1]] = i + 1, c = 0; }
}
induceSA(T, SA, C, B, n, k);
}
/* compact all the sorted substrings into the first m items of SA
2*m must be not larger than n (proveable) */
#ifdef _OPENMP
#pragma omp parallel for default(shared) private(i, j, p, c0, c1)
for(i = 0; i < n; ++i) {
p = SA[i];
if((0 < p) && (T[p - 1] > (c0 = T[p]))) {
for(j = p + 1; (j < n) && (c0 == (c1 = T[j])); ++j) { }
if((j < n) && (c0 < c1)) { SA[i] = ~p; }
}
}
for(i = 0, m = 0; i < n; ++i) { if((p = SA[i]) < 0) { SA[m++] = ~p; } }
#else
for(i = 0, m = 0; i < n; ++i) {
p = SA[i];
if((0 < p) && (T[p - 1] > (c0 = T[p]))) {
for(j = p + 1; (j < n) && (c0 == (c1 = T[j])); ++j) { }
if((j < n) && (c0 < c1)) {
SA[m++] = p; }
}
}
#endif
j = m + (n >> 1);
#ifdef _OPENMP
#pragma omp parallel for default(shared) private(i)
#endif
for(i = m; i < j; ++i) { SA[i] = 0; } /* init the name array buffer */
/* store the length of all substrings */
for(i = n - 2, j = n, c = 0, c1 = T[n - 1]; 0 <= i; --i, c1 = c0) {
if((c0 = T[i]) < (c1 + c)) { c = 1; }
else if(c != 0) { SA[m + ((i + 1) >> 1)] = j - i - 1; j = i + 1; c = 0; }
}
/* find the lexicographic names of all substrings */
for(i = 0, name = 0, q = n, qlen = 0; i < m; ++i) {
p = SA[i], plen = SA[m + (p >> 1)], diff = true;
if(plen == qlen) {
for(j = 0; (j < plen) && (T[p + j] == T[q + j]); ++j) { }
if(j == plen) { diff = false; }
}
if(diff != false) { ++name, q = p, qlen = plen; }
SA[m + (p >> 1)] = name;
}
/* stage 2: solve the reduced problem
recurse if names are not yet unique */
if(name < m) {
RA = SA + n + fs - m;
for(i = m + (n >> 1) - 1, j = m - 1; m <= i; --i) {
if(SA[i] != 0) { RA[j--] = SA[i] - 1; }
}
if(suffixsort(RA, SA, fs + n - m * 2, m, name, false) != 0) { return -2; }
for(i = n - 2, j = m - 1, c = 0, c1 = T[n - 1]; 0 <= i; --i, c1 = c0) {
if((c0 = T[i]) < (c1 + c)) { c = 1; }
else if(c != 0) { RA[j--] = i + 1, c = 0; } /* get p1 */
}
#ifdef _OPENMP
#pragma omp parallel for default(shared) private(i)
#endif
for(i = 0; i < m; ++i) { SA[i] = RA[SA[i]]; } /* get index in s */
}
/* stage 3: induce the result for the original problem */
if(fs < (maxthreads * k)) {
index_type *B, *C;
if((C = new index_type[maxthreads * k]) == 0) { return -2; }
B = (1 < maxthreads) ? C + k : C;
/* put all left-most S characters into their buckets */
getCounts(T, C, n, k); getBuckets(C, B, k, true); /* find ends of buckets */
#ifdef _OPENMP
#pragma omp parallel for default(shared) private(i)
#endif
for(i = m; i < n; ++i) { SA[i] = 0; } /* init SA[m..n-1] */
for(i = m - 1; 0 <= i; --i) {
j = SA[i], SA[i] = 0;
SA[--B[T[j]]] = j;
}
if(isbwt == false) { induceSA(T, SA, C, B, n, k); }
else { pidx = computeBWT(T, SA, C, B, n, k); }
delete [] C;
} else {
sarray_type C, B;
C = SA + n;
B = ((1 < maxthreads) || (k <= (fs - k))) ? C + k : C;
/* put all left-most S characters into their buckets */
getCounts(T, C, n, k); getBuckets(C, B, k, true); /* find ends of buckets */
#ifdef _OPENMP
#pragma omp parallel for default(shared) private(i)
#endif
for(i = m; i < n; ++i) { SA[i] = 0; } /* init SA[m..n-1] */
for(i = m - 1; 0 <= i; --i) {
j = SA[i], SA[i] = 0;
SA[--B[T[j]]] = j;
}
if(isbwt == false) { induceSA(T, SA, C, B, n, k); }
else { pidx = computeBWT(T, SA, C, B, n, k); }
}
return pidx;
#ifndef _OPENMP
# undef maxthreads
#endif
}
} /* namespace saisxx_private */
/**
* @brief Constructs the suffix array of a given string in linear time.
* @param T[0..n-1] The input string. (random access iterator)
* @param SA[0..n-1] The output array of suffixes. (random access iterator)
* @param n The length of the given string.
* @param k The alphabet size.
* @return 0 if no error occurred, -1 or -2 otherwise.
*/
template<typename string_type, typename sarray_type, typename index_type>
int
saisxx(string_type T, sarray_type SA, index_type n, index_type k = 256) {
int err;
if((n < 0) || (k <= 0)) { return -1; }
if(n <= 1) { if(n == 1) { SA[0] = 0; } return 0; }
try { err = saisxx_private::suffixsort(T, SA, index_type(0), n, k, false); }
catch(...) { err = -2; }
return err;
}
/**
* @brief Constructs the burrows-wheeler transformed string of a given string in linear time.
* @param T[0..n-1] The input string. (random access iterator)
* @param U[0..n-1] The output string. (random access iterator)
* @param A[0..n-1] The temporary array. (random access iterator)
* @param n The length of the given string.
* @param k The alphabet size.
* @return The primary index if no error occurred, -1 or -2 otherwise.
*/
template<typename string_type, typename sarray_type, typename index_type>
index_type
saisxx_bwt(string_type T, string_type U, sarray_type A, index_type n, index_type k = 256) {
typedef typename std::iterator_traits<string_type>::value_type char_type;
index_type i, pidx;
if((n < 0) || (k <= 0)) { return -1; }
if(n <= 1) { if(n == 1) { U[0] = T[0]; } return n; }
try {
pidx = saisxx_private::suffixsort(T, A, 0, n, k, true);
if(0 <= pidx) {
U[0] = T[n - 1];
for(i = 0; i < pidx; ++i) { U[i + 1] = (char_type)A[i]; }
for(i += 1; i < n; ++i) { U[i] = (char_type)A[i]; }
pidx += 1;
}
} catch(...) { pidx = -2; }
return pidx;
}
#endif /* __cplusplus */
#endif /* _SAIS_HXX */
+485
View File
@@ -0,0 +1,485 @@
use crate::types::{Bucket, SArray, StringT, SuffixError};
fn has_high_bit(j: usize) -> bool {
j > usize::MAX / 2
}
fn get_counts(t: &StringT, c: &mut Bucket) {
c.iter_mut().for_each(|c| *c = 0);
t.iter().for_each(|character| c[*character as usize] += 1);
}
fn get_buckets(c: &Bucket, b: &mut Bucket, _k: usize, end: bool) {
let mut sum = 0;
if end {
b.iter_mut().enumerate().for_each(|(i, b_el)| {
sum += c[i];
*b_el = sum;
});
} else {
b.iter_mut().enumerate().for_each(|(i, b_el)| {
*b_el = sum;
sum += c[i];
});
}
}
fn induce_sa(
string: &StringT,
suffix_array: &mut SArray,
counts: &mut Bucket,
buckets: &mut Bucket,
n: usize,
k: usize,
) {
assert!(n <= suffix_array.len());
get_counts(string, counts);
get_buckets(counts, buckets, k, false);
let mut c0;
let mut j = n - 1;
let mut c1 = string[j] as usize;
let mut index = buckets[c1];
suffix_array[index] = if j > 0 && (string[j - 1] as usize) < c1 {
!j
} else {
j
};
index += 1;
for i in 0..n {
j = suffix_array[i];
suffix_array[i] = !j;
if !has_high_bit(j) && j > 0 {
j -= 1;
c0 = string[j] as usize;
if c0 != c1 {
buckets[c1] = index;
c1 = c0;
index = buckets[c1];
}
suffix_array[index] = if j > 0 && !has_high_bit(j) && (string[j - 1] as usize) < c1 {
!j
} else {
j
};
index += 1;
}
}
// Compute SA
// XXX: true here.
get_counts(string, counts);
get_buckets(counts, buckets, k, true);
c1 = 0;
index = buckets[c1];
for i in (0..n).rev() {
j = suffix_array[i];
if j > 0 && !has_high_bit(j) {
j -= 1;
c0 = string[j] as usize;
if c0 != c1 {
buckets[c1] = index;
c1 = c0;
index = buckets[c1];
}
index -= 1;
suffix_array[index] = if j == 0 || (string[j - 1] as usize) > c1 {
!j
} else {
j
};
} else {
suffix_array[i] = !j;
}
}
}
fn compute_bwt(
string: &StringT,
suffix_array: &mut SArray,
counts: &mut Bucket,
buckets: &mut Bucket,
n: usize,
k: usize,
) -> usize {
// TODO
let mut pidx = 0;
get_counts(string, counts);
get_buckets(counts, buckets, k, false);
let mut j = n - 1;
let mut c1 = string[j] as usize;
let mut c0;
let mut index = buckets[c1];
// bb = SA + B[c1 = T[j = n - 1]];
// *bb++ = ((0 < j) && (T[j - 1] < c1)) ? ~j : j;
suffix_array[index] = if j > 0 && (string[j - 1] as usize) < c1 {
!j
} else {
j
};
index += 1;
for i in 0..n {
j = suffix_array[i];
if j > 0 {
j -= 1;
c0 = string[j] as usize;
suffix_array[i] = !c0;
if c0 != c1 {
buckets[c1] = index;
c1 = c0;
index = buckets[c1];
}
suffix_array[index] = if j > 0 && (string[j - 1] as usize) < c1 {
!j
} else {
j
};
index += 1;
} else if j != 0 {
suffix_array[i] = !j;
}
}
// Compute SA
get_counts(string, counts);
get_buckets(counts, buckets, k, true);
c1 = 0;
index = buckets[c1];
for i in (0..n).rev() {
j = suffix_array[i];
if j > 0 {
j -= 1;
c0 = string[j] as usize;
suffix_array[i] = c0;
if c0 != c1 {
buckets[c1] = index;
c1 = c0;
index = buckets[c1];
}
index -= 1;
suffix_array[index] = if j > 0 && (string[j - 1] as usize) > c1 {
!(string[j - 1] as usize)
} else {
j
};
} else if j != 0 {
suffix_array[i] = !j;
} else {
pidx = i
}
}
pidx
}
#[allow(clippy::many_single_char_names)]
fn suffixsort(
string: &StringT,
suffix_array: &mut SArray,
fs: usize,
n: usize,
k: usize,
is_bwt: bool,
) -> Result<usize, SuffixError> {
let mut pidx = 0;
let mut c0;
let mut counts = vec![0; k];
let mut buckets = vec![0; k];
get_counts(string, &mut counts);
get_buckets(&counts, &mut buckets, k, true);
// stage 1:
// reduce the problem by at least 1/2
// sort all the S-substrings
for item in suffix_array.iter_mut() {
*item = 0;
}
let mut c_index = 0;
let mut c1 = string[n - 1] as usize;
for i in (0..n - 1).rev() {
c0 = string[i] as usize;
if c0 < c1 + c_index {
c_index = 1;
} else if c_index != 0 {
buckets[c1] -= 1;
suffix_array[buckets[c1]] = i + 1;
c_index = 0;
}
c1 = c0;
}
induce_sa(string, suffix_array, &mut counts, &mut buckets, n, k);
// compact all the sorted substrings into the first m items of SA
// 2*m must be not larger than n (proveable)
// TODO: This was in the parallel loop.
let mut p;
let mut j;
let mut m = 0;
for i in 0..n {
p = suffix_array[i];
c0 = string[p] as usize;
if p > 0 && (string[p - 1] as usize) > c0 {
// TODO overly complex. But fricking hard to get right.
j = p + 1;
if j < n {
c1 = string[j] as usize;
}
while j < n && c0 == c1 {
c1 = string[j] as usize;
j += 1;
}
if j < n && c0 < c1 {
suffix_array[m] = p;
m += 1;
}
}
}
j = m + (n >> 1);
for item in suffix_array.iter_mut().take(j).skip(m) {
*item = 0;
}
/* store the length of all substrings */
j = n;
let mut c_index = 0;
c1 = string[n - 1] as usize;
for i in (0..n - 1).rev() {
c0 = string[i] as usize;
if c0 < c1 + c_index {
c_index = 1;
} else if c_index != 0 {
suffix_array[m + ((i + 1) >> 1)] = j - i - 1;
j = i + 1;
c_index = 0;
}
c1 = c0;
}
/* find the lexicographic names of all substrings */
let mut name = 0;
let mut q = n;
let mut qlen = 0;
let mut plen;
let mut diff;
for i in 0..m {
p = suffix_array[i];
plen = suffix_array[m + (p >> 1)];
diff = true;
if plen == qlen {
j = 0;
while j < plen && string[p + j] == string[q + j] {
j += 1;
}
if j == plen {
diff = false;
}
}
if diff {
name += 1;
q = p;
qlen = plen;
}
suffix_array[m + (p >> 1)] = name;
}
/* stage 2: solve the reduced problem
recurse if names are not yet unique */
if name < m {
let ra_index = n + fs - m;
j = m - 1;
let a = m + (n >> 1);
for i in (m..a).rev() {
if suffix_array[i] != 0 {
suffix_array[ra_index + j] = suffix_array[i] - 1;
// XXX: Bug underflow caught by Rust yeah (well cpp used i32)
j = j.saturating_sub(1);
}
}
// XXX: Could call transmute on SA to avoid allocation.
// but it requires unsafe.
let ra: Vec<u32> = suffix_array
.iter()
.skip(ra_index)
.take(m)
.map(|n| *n as u32)
.collect();
suffixsort(&ra, suffix_array, fs + n - m * 2, m, name, false)?;
// let ra: &[char] =
// unsafe { std::mem::transmute::<&[usize], &[char]>(&sa[ra_index..ra_index + m]) };
// suffixsort(ra, sa, fs + n - m * 2, m, name, false)?;
j = m - 1;
c_index = 0;
c1 = string[n - 1] as usize;
for i in (0..n - 1).rev() {
c0 = string[i] as usize;
if c0 < c1 + c_index {
c_index = 1;
} else if c_index != 0 {
suffix_array[ra_index + j] = i + 1;
c_index = 0;
j = j.saturating_sub(1);
}
c1 = c0;
}
// get index in s
for i in 0..m {
suffix_array[i] = suffix_array[ra_index + suffix_array[i]];
}
}
/* stage 3: induce the result for the original problem */
/* put all left-most S characters into their buckets */
get_counts(string, &mut counts);
get_buckets(&counts, &mut buckets, k, true);
for item in suffix_array.iter_mut().take(n).skip(m) {
*item = 0;
}
for i in (0..m).rev() {
j = suffix_array[i];
suffix_array[i] = 0;
if buckets[string[j] as usize] > 0 {
buckets[string[j] as usize] -= 1;
suffix_array[buckets[string[j] as usize]] = j;
}
}
if is_bwt {
pidx = compute_bwt(string, suffix_array, &mut counts, &mut buckets, n, k);
} else {
induce_sa(string, suffix_array, &mut counts, &mut buckets, n, k);
}
Ok(pidx)
}
pub fn saisxx(
string: &StringT,
suffix_array: &mut SArray,
n: usize,
k: usize,
) -> Result<(), SuffixError> {
if n == 1 {
suffix_array[0] = 0;
return Ok(());
}
let fs = 0;
suffixsort(string, suffix_array, fs, n, k, false)?;
Ok(())
}
fn _saisxx_bwt(
t: &StringT,
u: &mut StringT,
sa: &mut SArray,
n: usize,
k: usize,
) -> Result<usize, SuffixError> {
if n <= 1 {
if n == 1 {
u[0] = t[0];
}
return Ok(n);
}
let mut pidx = suffixsort(t, sa, 0, n, k, true)?;
u[0] = t[n - 1];
for i in 0..pidx {
u[i + 1] = sa[i] as u32;
}
for i in pidx + 1..n {
u[i] = sa[i] as u32
}
pidx += 1;
Ok(pidx)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_induce_sa() {
let chars: Vec<_> = "abracadabra".chars().map(|c| c as u32).collect();
let mut c = vec![0; 256];
let mut b = vec![0; 256];
let mut sa = vec![0, 0, 3, 5, 7, 0, 0, 0, 0, 0, 0];
induce_sa(&chars, &mut sa, &mut b, &mut c, chars.len(), 256);
assert_eq!(sa, vec![10, 7, 0, 3, 5, 8, 1, 4, 6, 9, 2]);
let mut sa = vec![0, 0, 7, 3, 5, 0, 0, 0, 0, 0, 0];
induce_sa(&chars, &mut sa, &mut b, &mut c, chars.len(), 256);
assert_eq!(sa, vec![10, 7, 0, 3, 5, 8, 1, 4, 6, 9, 2]);
}
#[test]
fn test_induce_sa_long() {
let string = "Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.".to_string();
let chars: Vec<_> = string.chars().map(|c| c as u32).collect();
let mut c = vec![0; 256];
let mut b = vec![0; 256];
let mut sa = vec![
5, 11, 14, 21, 27, 32, 35, 39, 48, 52, 64, 74, 80, 86, 90, 95, 99, 110, 119, 125, 130,
135, 141, 145, 152, 157, 160, 168, 176, 181, 183, 190, 193, 198, 202, 212, 215, 218,
223, 225, 230, 239, 245, 248, 252, 261, 265, 270, 275, 286, 290, 295, 299, 304, 309,
320, 333, 343, 355, 366, 369, 373, 385, 388, 392, 398, 403, 407, 415, 418, 427, 434,
445, 451, 457, 467, 471, 476, 485, 490, 498, 509, 518, 523, 529, 539, 549, 558, 561,
567, 108, 0, 0, 0, 0, 0, 0, 0, 0, 0, 148, 396, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 534, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 88, 113, 116, 185, 206, 220, 250, 302,
337, 351, 360, 371, 379, 412, 423, 439, 459, 462, 515, 0, 0, 0, 208, 501, 0, 0, 0, 139,
204, 234, 313, 358, 479, 542, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 67, 102, 526, 545, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 3, 29, 56, 58, 78, 127, 133, 155, 174, 188, 237, 283, 324, 326, 335,
347, 409, 425, 430, 449, 464, 537, 551, 565, 0, 0, 0, 0, 0, 512, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 505, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 16, 42, 45, 61, 137, 171, 257, 329, 340, 381, 400, 442, 487, 503,
520, 554, 0, 0, 0, 0, 0, 163, 494, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, 268,
483, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 122, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
437, 556, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 375,
496, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 71, 106, 255, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 69, 104, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
];
assert_eq!(sa.len(), chars.len());
induce_sa(&chars, &mut sa, &mut b, &mut c, chars.len(), 256);
assert_eq!(
sa,
vec![
145, 392, 523, 5, 80, 451, 567, 245, 366, 418, 74, 445, 561, 529, 181, 223, 290,
157, 48, 198, 467, 90, 239, 286, 275, 434, 490, 21, 119, 309, 343, 130, 270, 183,
86, 248, 385, 539, 64, 99, 304, 11, 212, 299, 518, 218, 471, 261, 32, 190, 415,
558, 265, 457, 373, 39, 168, 498, 476, 333, 407, 202, 427, 14, 135, 509, 230, 110,
252, 27, 125, 35, 95, 141, 295, 388, 403, 215, 176, 193, 225, 52, 320, 355, 160,
549, 369, 152, 398, 485, 108, 151, 285, 332, 466, 573, 73, 244, 365, 148, 396, 149,
146, 393, 147, 395, 394, 524, 6, 81, 452, 568, 246, 367, 419, 0, 75, 446, 562, 534,
530, 182, 224, 531, 462, 337, 439, 220, 535, 185, 351, 291, 206, 158, 49, 199, 468,
113, 360, 302, 116, 515, 379, 88, 250, 371, 412, 423, 459, 91, 208, 501, 240, 287,
319, 139, 479, 276, 358, 234, 542, 435, 204, 313, 51, 118, 201, 211, 260, 384, 470,
364, 115, 491, 545, 22, 120, 526, 67, 102, 38, 98, 140, 144, 197, 222, 229, 274,
298, 391, 406, 414, 475, 517, 522, 533, 301, 411, 233, 312, 478, 210, 259, 383,
363, 92, 430, 409, 310, 3, 78, 449, 565, 335, 93, 155, 237, 347, 480, 277, 133,
174, 537, 551, 283, 464, 56, 324, 492, 344, 425, 420, 431, 58, 326, 131, 29, 127,
188, 34, 192, 417, 560, 271, 512, 47, 63, 342, 444, 508, 548, 331, 184, 532, 362,
463, 402, 489, 87, 249, 359, 37, 97, 143, 297, 390, 405, 154, 429, 505, 350, 318,
282, 520, 235, 16, 386, 137, 540, 65, 100, 45, 61, 340, 442, 506, 546, 329, 338,
440, 171, 42, 305, 554, 12, 381, 503, 213, 400, 487, 272, 257, 180, 243, 221, 521,
536, 163, 494, 378, 525, 300, 410, 311, 209, 187, 502, 519, 186, 352, 292, 543, 19,
268, 353, 483, 4, 10, 79, 85, 450, 456, 566, 572, 219, 336, 207, 236, 24, 122, 472,
17, 25, 123, 94, 156, 159, 167, 238, 387, 138, 357, 541, 50, 200, 469, 114, 66,
101, 46, 62, 341, 443, 507, 547, 330, 361, 317, 339, 441, 162, 267, 262, 164, 556,
437, 172, 348, 43, 481, 306, 278, 217, 294, 308, 33, 191, 416, 559, 511, 179, 242,
316, 266, 436, 555, 178, 241, 496, 375, 473, 1, 76, 447, 563, 263, 165, 303, 497,
458, 196, 228, 232, 55, 323, 18, 374, 40, 169, 7, 82, 453, 569, 499, 376, 134, 175,
538, 205, 422, 117, 474, 516, 477, 2, 77, 334, 408, 448, 564, 281, 41, 170, 380,
315, 552, 255, 106, 71, 13, 89, 109, 251, 372, 397, 433, 528, 557, 150, 284, 465,
461, 203, 413, 382, 57, 325, 346, 424, 428, 504, 15, 136, 553, 493, 293, 510, 231,
460, 345, 111, 69, 104, 8, 83, 454, 570, 253, 31, 129, 214, 247, 264, 289, 368,
426, 112, 438, 28, 126, 173, 401, 488, 36, 96, 142, 296, 389, 404, 349, 44, 60,
328, 482, 216, 307, 177, 495, 421, 314, 70, 105, 432, 59, 327, 279, 513, 194, 226,
53, 321, 500, 544, 377, 9, 84, 455, 571, 23, 121, 356, 161, 280, 254, 527, 68, 103,
288, 273, 258, 132, 550, 256, 370, 514, 153, 399, 486, 166, 30, 128, 20, 26, 124,
189, 269, 354, 484, 107, 72, 195, 227, 54, 322
]
);
}
}
+19
View File
@@ -0,0 +1,19 @@
pub type Bucket = [usize];
/// We need to use u32 instead of char, because when we recurse
/// we use suffix array elements as ways to replace our original
/// string. Using chars can fail. Look for ra variable.
pub type StringT = [u32];
pub type SArray = [usize];
#[derive(Debug)]
pub enum SuffixError {
InvalidLength,
Internal,
IntConversion(std::num::TryFromIntError),
}
impl From<std::num::TryFromIntError> for SuffixError {
fn from(err: std::num::TryFromIntError) -> Self {
Self::IntConversion(err)
}
}