Feat/generated app suite

.vscode/settings.json

@@ -1,11 +1,19 @@
 {
-    "python-envs.defaultEnvManager": "ms-python.python:conda",
-    "python-envs.defaultPackageManager": "ms-python.python:conda",
-    "python-envs.pythonProjects": [
-        {
-            "path": ".",
-            "envManager": "ms-python.python:conda",
-            "packageManager": "ms-python.python:conda"
-        }
-    ]
+  "python.analysis.extraPaths": [
+    "apps/src",
+    "../../SAGE/src"
+  ],
+  "python.autoComplete.extraPaths": [
+    "apps/src",
+    "../../SAGE/src"
+  ],
+  "python-envs.defaultEnvManager": "ms-python.python:conda",
+  "python-envs.defaultPackageManager": "ms-python.python:conda",
+  "python-envs.pythonProjects": [
+    {
+      "path": ".",
+      "envManager": "ms-python.python:conda",
+      "packageManager": "ms-python.python:conda"
+    }
+  ]
 }

README.md

@@ -38,7 +38,7 @@ python examples/run_video_intelligence.py
 
 ## 📁 Repository Structure
 
-```
+```text
 sage-examples/
 ├── examples/                  # 🎯 Production application examples
 │   ├── run_video_intelligence.py
@@ -81,7 +81,21 @@ Complete, runnable applications demonstrating real-world use cases:
 | 🎫 **Ticket Triage**             | Stateful customer support ticket classification, urgency scoring, and routing | `examples/run_ticket_triage.py`               |
 | 🌐 **Ticket Triage API**         | FastAPI service for triage ingestion, queue queries, and ticket lookup        | `examples/run_ticket_triage_api.py`           |
 
-See `examples/README.md` for details.
+The repository also includes the full 53-91 domain app suite across research, education, healthcare,
+enterprise operations, public service, sustainability, and infrastructure monitoring.
+
+Representative newer entry points include:
+
+- `examples/run_patent_competition_monitor.py`
+- `examples/run_campus_aid_gap_alert.py`
+- `examples/run_lab_turnaround_alert.py`
+- `examples/run_policy_search_helper.py`
+- `examples/run_community_hotspot_drift.py`
+- `examples/run_budget_variance_alert.py`
+- `examples/run_carbon_collection.py`
+- `examples/run_data_center_watch.py`
+
+See `examples/README.md` for the complete runnable script index.
 
 ## 📦 Installation
 
@@ -107,7 +121,7 @@ pip install -e .[dev]
 
 SAGE uses a strict 6-layer architecture with unidirectional dependencies:
 
-```
+```text
 ┌─────────────────────────────────────────────┐
 │ L6: Interface                                │  CLI, Web UI, Tools
 ├─────────────────────────────────────────────┤
@@ -180,15 +194,16 @@ See `docs/DEVELOPMENT.md` for complete development guide.
 - **Development Guide**: `docs/DEVELOPMENT.md` - Contributing
 - **SAGE Tutorials**: [SAGE/tutorials](https://github.com/intellistream/SAGE/tree/main/tutorials) -
   Learn SAGE
-- **SAGE Docs**: https://intellistream.github.io/SAGE
+- **SAGE Docs**: [intellistream.github.io/SAGE](https://intellistream.github.io/SAGE)
 
 ## 🤝 Contributing
 
 We welcome contributions! Please see:
 
 1. **Development Guide**: `docs/DEVELOPMENT.md`
 1. **Code of Conduct**: Follow respectful collaboration
-1. **Issue Tracker**: https://github.com/intellistream/sage-examples/issues
+1. **Issue Tracker**:
+   [github.com/intellistream/sage-examples/issues](https://github.com/intellistream/sage-examples/issues)
 
 ### Adding Examples
 
@@ -201,9 +216,10 @@ We welcome contributions! Please see:
 
 ## 🔗 Related Repositories
 
-- **SAGE Main**: https://github.com/intellistream/SAGE
-- **SAGE Benchmark**: https://github.com/intellistream/sage-benchmark
-- **PyPI Packages**: https://pypi.org/search/?q=isage
+- **SAGE Main**: [github.com/intellistream/SAGE](https://github.com/intellistream/SAGE)
+- **SAGE Benchmark**:
+  [github.com/intellistream/sage-benchmark](https://github.com/intellistream/sage-benchmark)
+- **PyPI Packages**: [pypi.org/search/?q=isage](https://pypi.org/search/?q=isage)
 
 ## 📄 License
 
@@ -221,4 +237,4 @@ If you find this project helpful, please consider giving it a ⭐️!
 
 ______________________________________________________________________
 
-**Made with ❤️ by the IntelliStream Team**
+Made with ❤️ by the IntelliStream Team.

apps/src/sage/apps/_batch.py

@@ -0,0 +1,27 @@
+from __future__ import annotations
+
+from typing import Any
+
+from sage.foundation import BatchFunction
+
+
+class ListBatchSource(BatchFunction):
+    def __init__(self, *args, **kwargs) -> None:
+        super().__init__(*args, **kwargs)
+        self._batch_items: list[Any] | None = None
+        self._batch_index = 0
+
+    def load_items(self) -> list[Any]:
+        raise NotImplementedError
+
+    def execute(self) -> Any | None:
+        if self._batch_items is None:
+            self._batch_items = list(self.load_items())
+            self._batch_index = 0
+
+        if self._batch_index >= len(self._batch_items):
+            return None
+
+        item = self._batch_items[self._batch_index]
+        self._batch_index += 1
+        return item

apps/src/sage/apps/academic_metadata/README.md

@@ -0,0 +1,18 @@
+# Academic Metadata
+
+学术文献元数据抽取应用。
+
+## 功能
+
+- 从目录、单文件或 CSV 读取文献文本
+- 提取标题、作者、年份、DOI、邮箱与摘要
+- 标准化作者名称
+- 输出 JSON 结果
+
+## 用法
+
+```bash
+python examples/run_academic_metadata.py \
+  --input-path sample_papers \
+  --output metadata.json
+```

apps/src/sage/apps/academic_metadata/__init__.py

@@ -0,0 +1,5 @@
+"""Academic metadata extraction application."""
+
+from .pipeline import run_academic_metadata_pipeline
+
+__all__ = ["run_academic_metadata_pipeline"]

apps/src/sage/apps/academic_metadata/operators.py

@@ -0,0 +1,137 @@
+"""Operators for academic metadata extraction."""
+
+from __future__ import annotations
+
+import csv
+import json
+import re
+from pathlib import Path
+from typing import Any
+
+from sage.apps._batch import ListBatchSource
+from sage.foundation import CustomLogger, MapFunction, SinkFunction
+
+
+class PdfSource(ListBatchSource):
+    def __init__(self, input_path: str, **kwargs):
+        super().__init__(**kwargs)
+        self.input_path = Path(input_path)
+        self._logger = CustomLogger("PdfSource")
+
+    def load_items(self) -> list[dict[str, Any]]:
+        items: list[dict[str, Any]] = []
+        if self.input_path.is_dir():
+            for file_path in sorted(self.input_path.iterdir()):
+                if file_path.is_file() and file_path.suffix.lower() in {".txt", ".md"}:
+                    items.append(
+                        {
+                            "source_file": str(file_path),
+                            "text": file_path.read_text(encoding="utf-8"),
+                        }
+                    )
+        elif self.input_path.suffix.lower() == ".csv":
+            with self.input_path.open("r", encoding="utf-8", newline="") as handle:
+                for row in csv.DictReader(handle):
+                    items.append(
+                        {"source_file": row.get("source_file", ""), "text": row.get("text", "")}
+                    )
+        else:
+            items.append(
+                {
+                    "source_file": str(self.input_path),
+                    "text": self.input_path.read_text(encoding="utf-8"),
+                }
+            )
+        self.logger.info(f"Loaded {len(items)} academic documents")
+        return items
+
+
+class TextExtractor(MapFunction):
+    def execute(self, item: dict[str, Any]) -> dict[str, Any]:
+        result = dict(item)
+        result["text"] = str(item.get("text", ""))
+        return result
+
+
+class MetadataExtractor(MapFunction):
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self._logger = CustomLogger("MetadataExtractor")
+
+    def execute(self, item: dict[str, Any]) -> dict[str, Any]:
+        text = item.get("text", "")
+        lines = [line.strip() for line in text.splitlines() if line.strip()]
+        title = lines[0] if lines else ""
+        doi_match = re.search(r"10\.\d{4,9}/[-._;()/:A-Z0-9]+", text, flags=re.IGNORECASE)
+        year_match = re.search(r"\b(19|20)\d{2}\b", text)
+        email_matches = re.findall(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}", text)
+        author_line = ""
+        for line in lines[1:6]:
+            if "," in line or " and " in line.lower() or len(line.split()) <= 12:
+                author_line = line
+                break
+        authors = [part.strip() for part in re.split(r",| and |;", author_line) if part.strip()]
+        result = dict(item)
+        result.update(
+            {
+                "title": title,
+                "authors": authors,
+                "year": year_match.group(0) if year_match else "",
+                "doi": doi_match.group(0) if doi_match else "",
+                "emails": email_matches,
+                "abstract": self._extract_abstract(text),
+            }
+        )
+        return result
+
+    def _extract_abstract(self, text: str) -> str:
+        lowered = text.lower()
+        marker = lowered.find("abstract")
+        if marker == -1:
+            return ""
+
+        snippet = text[marker:]
+        lines = [line.strip() for line in snippet.splitlines()]
+        abstract_lines: list[str] = []
+        started = False
+        for line in lines:
+            if not started:
+                if line.lower().startswith("abstract"):
+                    remainder = line.split(":", 1)[1].strip() if ":" in line else ""
+                    if remainder:
+                        abstract_lines.append(remainder)
+                    started = True
+                continue
+
+            lowered_line = line.lower()
+            if not line or lowered_line.startswith("keywords"):
+                break
+            abstract_lines.append(line)
+
+        return " ".join(abstract_lines).strip()[:1200]
+
+
+class AuthorNormalizer(MapFunction):
+    def execute(self, item: dict[str, Any]) -> dict[str, Any]:
+        normalized = []
+        for author in item.get("authors", []):
+            cleaned = " ".join(author.replace("*", " ").split())
+            if cleaned:
+                normalized.append(cleaned.title())
+        item["authors"] = normalized
+        item["has_complete_metadata"] = bool(item.get("title") and item.get("authors"))
+        return item
+
+
+class MetadataSink(SinkFunction):
+    def __init__(self, output_file: str, **kwargs):
+        super().__init__(**kwargs)
+        self.output_file = output_file
+        self.items: list[dict[str, Any]] = []
+
+    def execute(self, item: dict[str, Any]) -> None:
+        self.items.append(item)
+
+    def teardown(self, context: Any) -> None:
+        with open(self.output_file, "w", encoding="utf-8") as handle:
+            json.dump(self.items, handle, ensure_ascii=False, indent=2)

apps/src/sage/apps/academic_metadata/pipeline.py

@@ -0,0 +1,28 @@
+"""Academic metadata pipeline."""
+
+from __future__ import annotations
+
+from sage.foundation import CustomLogger
+from sage.runtime import LocalEnvironment
+
+from .operators import AuthorNormalizer, MetadataExtractor, MetadataSink, PdfSource, TextExtractor
+
+
+def run_academic_metadata_pipeline(
+    input_path: str,
+    output_file: str,
+    verbose: bool = False,
+) -> None:
+    logger = CustomLogger("AcademicMetadataPipeline")
+    if verbose:
+        logger.info(f"Starting academic metadata extraction: {input_path}")
+
+    env = LocalEnvironment("academic_metadata")
+    (
+        env.from_batch(PdfSource, input_path=input_path)
+        .map(TextExtractor)
+        .map(MetadataExtractor)
+        .map(AuthorNormalizer)
+        .sink(MetadataSink, output_file=output_file)
+    )
+    env.submit(autostop=True)

apps/src/sage/apps/api_log_analytics/README.md

@@ -0,0 +1,5 @@
+# API Log Analytics
+
+读取 API 日志，解析状态码和时延并识别异常请求。
+
+输入：CSV 或 JSON API 日志。 输出：包含指标提取和异常判断的 JSON 文件。

apps/src/sage/apps/api_log_analytics/__init__.py

@@ -0,0 +1,5 @@
+"""API log analytics application."""
+
+from .pipeline import run_api_log_analytics_pipeline
+
+__all__ = ["run_api_log_analytics_pipeline"]