rust-crate-pipeline 1.3.2__py3-none-any.whl → 1.3.3__py3-none-any.whl

rust_crate_pipeline/network.py

@@ -1,327 +1,321 @@
-# network.py
-import os
-import sys
-import re
-import time
-import logging
-import requests
-from bs4 import BeautifulSoup, Tag
-from typing import Any, Union
-from .config import PipelineConfig
-
-# Import utilities
-# Add the parent directory to the path to import utils
-sys.path.insert(0, os.path.dirname(os.path.dirname(__file__)))
-
-
-class GitHubBatchClient:
-    def __init__(self, config: PipelineConfig) -> None:
-        self.config = config
-        # Simple headers without dependency on HTTPClientUtils
-        self.headers = {
-            "Accept": "application/vnd.github.v3+json",
-            "User-Agent": "SigilDERG-Data-Production/1.3.2",
-        }
-        if config.github_token:
-            self.headers["Authorization"] = f"token {config.github_token}"
-
-        # Simple session without dependency on HTTPClientUtils
-        self.session = requests.Session()
-        self.session.headers.update(self.headers)
-        self.remaining_calls = 5000
-        self.reset_time = 0
-
-    def check_rate_limit(self) -> None:
-        """Check and update current rate limit status"""
-        try:
-            response = self.session.get(
-                "https://api.github.com/rate_limit", headers=self.headers
-            )
-            if response.ok:
-                data = response.json()
-                self.remaining_calls = data["resources"]["core"]["remaining"]
-                self.reset_time = data["resources"]["core"]["reset"]
-
-                if self.remaining_calls < 100:
-                    reset_in = self.reset_time - time.time()
-                    logging.warning(
-                        f"GitHub API rate limit low: {self.remaining_calls} remaining. "
-                        f"Resets in {reset_in / 60:.1f} minutes"
-                    )
-        except Exception:
-            pass
-
-    def get_repo_stats(self, owner: str, repo: str) -> "dict[str, Any]":
-        """Get repository statistics"""
-        try:
-            url = f"https://api.github.com/repos/{owner}/{repo}"
-            response = self.session.get(url, headers=self.headers)
-            if response.ok:
-                return response.json()
-            else:
-                logging.warning(
-                    f"Failed to get repo stats for {owner}/{repo}: "
-                    f"{response.status_code}"
-                )
-                return {}
-        except Exception as e:
-            logging.error(f"Error fetching repo stats: {str(e)}")
-            return {}
-
-    def batch_get_repo_stats(self, repo_list: "list[str]") -> "dict[str, dict[str, Any]]":
-        """Get statistics for multiple repositories in a batch"""
-        self.check_rate_limit()
-
-        results: "dict[str, dict[str, Any]]" = {}
-        for repo_url in repo_list:
-            # Extract owner/repo from URL
-            match = re.search(r"github\.com/([^/]+)/([^/\.]+)", repo_url)
-            if not match:
-                continue
-
-            owner, repo = match.groups()
-            repo = repo.split(".")[0]  # Remove .git extension if present
-
-            # Get stats
-            stats = self.get_repo_stats(owner, repo)
-            results[repo_url] = stats
-
-            # Be nice to GitHub API
-            time.sleep(0.1)
-        return results
-
-
-class CrateAPIClient:
-    def __init__(self, config: PipelineConfig) -> None:
-        self.config = config
-        # Simple session without dependency on HTTPClientUtils
-        self.session = requests.Session()
-        self.session.headers.update({"User-Agent": "SigilDERG-Data-Production/1.3.2"})
-
-    def fetch_crate_metadata(self, crate_name: str) -> "dict[str, Any] | None":
-        """Fetch metadata with retry logic"""
-        for attempt in range(self.config.max_retries):
-            try:
-                return self._fetch_metadata(crate_name)
-            except Exception as e:
-                logging.warning(
-                    f"Attempt {
-                        attempt +
-                        1} failed for {crate_name}: {
-                        str(e)}"
-                )
-                wait = 2**attempt
-                time.sleep(wait)
-        return None
-
-    def _fetch_metadata(self, crate_name: str) -> "dict[str, Any] | None":
-        """Enhanced metadata fetching that tries multiple sources"""
-        # First try crates.io (primary source)
-        try:
-            r = self.session.get(f"https://crates.io/api/v1/crates/{crate_name}")
-            if r.ok:
-                data = r.json()
-                crate_data = data["crate"]
-                latest = crate_data["newest_version"]
-
-                # Get readme
-                readme_response = self.session.get(
-                    f"https://crates.io/api/v1/crates/{crate_name}/readme"
-                )
-                readme = readme_response.text if readme_response.ok else ""
-
-                # Get dependencies
-                deps_url = (
-                    f"https://crates.io/api/v1/crates/{crate_name}/"
-                    f"{latest}/dependencies"
-                )
-                deps_response = self.session.get(deps_url)
-                deps: list[dict[str, Any]] = (
-                    deps_response.json().get("dependencies", [])
-                    if deps_response.ok
-                    else []
-                )
-
-                # Get features - using the versions endpoint
-                features = []
-                versions_response = self.session.get(
-                    f"https://crates.io/api/v1/crates/{crate_name}/{latest}"
-                )
-                if versions_response.ok:
-                    version_data = versions_response.json().get("version", {})
-                    features_dict = version_data.get("features", {})
-                    features = [
-                        {"name": k, "dependencies": v} for k, v in features_dict.items()
-                    ]
-
-                # Repository info and GitHub stars
-                repo = crate_data.get("repository", "")
-                gh_stars = 0
-
-                # Check if it's a GitHub repo
-                if "github.com" in repo and self.config.github_token:
-                    match = re.search(r"github.com/([^/]+)/([^/]+)", repo)
-                    if match:
-                        owner, repo_name = match.groups()
-                        repo_name = repo_name.split(".")[0]  # Handle .git extensions
-                        gh_url = f"https://api.github.com/repos/{owner}/{repo_name}"
-                        gh_headers: dict[str, str] = {}
-                        if self.config.github_token:
-                            gh_headers["Authorization"] = (
-                                f"token {self.config.github_token}"
-                            )
-
-                        gh = self.session.get(gh_url, headers=gh_headers)
-                        if gh.ok:
-                            gh_data = gh.json()
-                            gh_stars = gh_data.get("stargazers_count", 0)
-
-                # Check if it's hosted on lib.rs
-                lib_rs_data = {}
-                if "lib.rs" in repo:
-                    lib_rs_url = f"https://lib.rs/crates/{crate_name}"
-                    lib_rs_response = self.session.get(lib_rs_url)
-                    if lib_rs_response.ok:
-                        soup = BeautifulSoup(lib_rs_response.text, "html.parser")
-                        # Get README from lib.rs if not already available
-                        if not readme:
-                            readme_div = soup.find("div", class_="readme")
-                            if readme_div:
-                                readme = readme_div.get_text(
-                                    strip=True
-                                )  # Get lib.rs specific stats
-                        stats_div = soup.find("div", class_="crate-stats")
-                        if isinstance(stats_div, Tag):
-                            downloads_text = stats_div.find(
-                                string=re.compile(r"[\d,]+ downloads")
-                            )
-                            if downloads_text:
-                                lib_rs_data["librs_downloads"] = int(
-                                    re.sub(r"[^\d]", "", str(downloads_text))
-                                )
-
-                # Extract code snippets and sections (simplified)
-                code_snippets: list[str] = (
-                    []
-                )  # Simplified - would normally extract from readme
-                readme_sections: dict[str, str] = (
-                    {}
-                )  # Simplified - would normally parse sections
-
-                result: dict[str, Any] = {
-                    "name": crate_name,
-                    "version": latest,
-                    "description": crate_data.get("description", ""),
-                    "repository": repo,
-                    "keywords": crate_data.get("keywords", []),
-                    "categories": crate_data.get("categories", []),
-                    "readme": readme,
-                    "downloads": crate_data.get("downloads", 0),
-                    "github_stars": gh_stars,
-                    "dependencies": deps,
-                    "code_snippets": code_snippets,
-                    "features": features,
-                    "readme_sections": readme_sections,
-                    **lib_rs_data,
-                }
-
-                return result
-
-        except Exception as e:
-            logging.error(
-                f"Failed fetching metadata for {crate_name}: {
-                    str(e)}"
-            )
-            raise
-
-        # If crates.io fails, try lib.rs
-        try:
-            r = self.session.get(f"https://lib.rs/crates/{crate_name}")
-            if r.ok:
-                soup = BeautifulSoup(r.text, "html.parser")
-
-                # Extract metadata from lib.rs page
-                h1 = soup.select_one("h1")
-                name = h1.text.strip() if h1 else crate_name
-
-                # Find description
-                desc_elem = soup.select_one(".description")
-                description = desc_elem.text.strip() if desc_elem else ""
-
-                # Find repository link
-                repo_link: Union[str, None] = None
-                for a in soup.select("a"):
-                    href = a.get("href")
-                    if href and isinstance(href, str) and "github.com" in href:
-                        repo_link = href
-                        break
-
-                # Find keywords
-                keywords_elem = soup.select_one(".keywords")
-                keywords = (
-                    [k.text.strip() for k in keywords_elem.find_all("a")]
-                    if keywords_elem
-                    else []
-                )
-
-                # Basic metadata from lib.rs
-                return {
-                    "name": name,
-                    "version": "latest",  # lib.rs doesn't easily expose version
-                    "description": description,
-                    "repository": repo_link or "",
-                    "keywords": keywords,
-                    "categories": [],
-                    "readme": "",
-                    "downloads": 0,
-                    "github_stars": 0,
-                    "dependencies": [],
-                    "code_snippets": [],
-                    "features": [],
-                    "readme_sections": {},
-                    "source": "lib.rs",
-                }
-        except Exception:
-            pass
-
-        # Finally, try GitHub search
-        try:
-            # This is a simplification - GitHub's search API requires
-            # authentication
-            gh_search_headers: dict[str, str] = {}
-            if self.config.github_token:
-                gh_search_headers["Authorization"] = f"token {self.config.github_token}"
-
-            search_url = (
-                f"https://api.github.com/search/repositories?"
-                f"q={crate_name}+language:rust"
-            )
-            r = requests.get(search_url, headers=gh_search_headers)
-
-            if r.ok:
-                results = r.json().get("items", [])
-                if results:
-                    repo = results[0]  # Take first match
-
-                    # Basic metadata from GitHub
-                    return {
-                        "name": crate_name,
-                        "version": "unknown",
-                        "description": repo.get("description", ""),
-                        "repository": repo.get("html_url", ""),
-                        "keywords": [],
-                        "categories": [],
-                        "readme": "",
-                        "downloads": 0,
-                        "github_stars": repo.get("stargazers_count", 0),
-                        "dependencies": [],
-                        "code_snippets": [],
-                        "features": [],
-                        "readme_sections": {},
-                        "source": "github",
-                    }
-        except Exception:
-            pass
-
-        # If all sources fail
-        return None
+# network.py
+import os
+import sys
+import re
+import time
+import logging
+import requests
+from bs4 import BeautifulSoup, Tag
+from typing import Any, Union
+from .config import PipelineConfig
+
+# Import utilities
+# Add the parent directory to the path to import utils
+sys.path.insert(0, os.path.dirname(os.path.dirname(__file__)))
+
+
+class GitHubBatchClient:
+    def __init__(self, config: PipelineConfig) -> None:
+        self.config = config
+        # Simple headers without dependency on HTTPClientUtils
+        self.headers = {
+            "Accept": "application/vnd.github.v3+json",
+            "User-Agent": "SigilDERG-Data-Production/1.3.2",
+        }
+        if config.github_token:
+            self.headers["Authorization"] = f"token {config.github_token}"
+
+        # Simple session without dependency on HTTPClientUtils
+        self.session = requests.Session()
+        self.session.headers.update(self.headers)
+        self.remaining_calls = 5000
+        self.reset_time = 0
+
+    def check_rate_limit(self) -> None:
+        """Check and update current rate limit status"""
+        try:
+            response = self.session.get(
+                "https://api.github.com/rate_limit", headers=self.headers
+            )
+            if response.ok:
+                data = response.json()
+                self.remaining_calls = data["resources"]["core"]["remaining"]
+                self.reset_time = data["resources"]["core"]["reset"]
+
+                if self.remaining_calls < 100:
+                    reset_in = self.reset_time - time.time()
+                    logging.warning(
+                        f"GitHub API rate limit low: {self.remaining_calls} remaining. Resets in {reset_in / 60:.1f} minutes"
+                    )
+        except Exception:
+            pass
+
+    def get_repo_stats(self, owner: str, repo: str) -> "dict[str, Any]":
+        """Get repository statistics"""
+        try:
+            url = f"https://api.github.com/repos/{owner}/{repo}"
+            response = self.session.get(url, headers=self.headers)
+            if response.ok:
+                return response.json()
+            else:
+                logging.warning(
+                    f"Failed to get repo stats for {owner}/{repo}: {response.status_code}"
+                )
+                return {}
+        except Exception as e:
+            logging.error(f"Error fetching repo stats: {str(e)}")
+            return {}
+
+    def batch_get_repo_stats(self, repo_list: "list[str]") -> "dict[str, dict[str, Any]]":
+        """Get statistics for multiple repositories in a batch"""
+        self.check_rate_limit()
+
+        results: "dict[str, dict[str, Any]]" = {}
+        for repo_url in repo_list:
+            # Extract owner/repo from URL
+            match = re.search(r"github\.com/([^/]+)/([^/\.]+)", repo_url)
+            if not match:
+                continue
+
+            owner, repo = match.groups()
+            repo = repo.split(".")[0]  # Remove .git extension if present
+
+            # Get stats
+            stats = self.get_repo_stats(owner, repo)
+            results[repo_url] = stats
+
+            # Be nice to GitHub API
+            time.sleep(0.1)
+        return results
+
+
+class CrateAPIClient:
+    def __init__(self, config: PipelineConfig) -> None:
+        self.config = config
+        # Simple session without dependency on HTTPClientUtils
+        self.session = requests.Session()
+        self.session.headers.update({"User-Agent": "SigilDERG-Data-Production/1.3.2"})
+
+    def fetch_crate_metadata(self, crate_name: str) -> "dict[str, Any] | None":
+        """Fetch metadata with retry logic"""
+        for attempt in range(self.config.max_retries):
+            try:
+                return self._fetch_metadata(crate_name)
+            except Exception as e:
+                logging.warning(
+                    f"Attempt {attempt + 1} failed for {crate_name}: {str(e)}"
+                )
+                wait = 2**attempt
+                time.sleep(wait)
+        return None
+
+    def _fetch_metadata(self, crate_name: str) -> "dict[str, Any] | None":
+        """Enhanced metadata fetching that tries multiple sources"""
+        # First try crates.io (primary source)
+        try:
+            r = self.session.get(f"https://crates.io/api/v1/crates/{crate_name}")
+            if r.ok:
+                data = r.json()
+                crate_data = data["crate"]
+                latest = crate_data["newest_version"]
+
+                # Get readme
+                readme_response = self.session.get(
+                    f"https://crates.io/api/v1/crates/{crate_name}/readme"
+                )
+                readme = readme_response.text if readme_response.ok else ""
+
+                # Get dependencies
+                deps_url = (
+                    f"https://crates.io/api/v1/crates/{crate_name}/"
+                    f"{latest}/dependencies"
+                )
+                deps_response = self.session.get(deps_url)
+                deps: list[dict[str, Any]] = (
+                    deps_response.json().get("dependencies", [])
+                    if deps_response.ok
+                    else []
+                )
+
+                # Get features - using the versions endpoint
+                features = []
+                versions_response = self.session.get(
+                    f"https://crates.io/api/v1/crates/{crate_name}/{latest}"
+                )
+                if versions_response.ok:
+                    version_data = versions_response.json().get("version", {})
+                    features_dict = version_data.get("features", {})
+                    features = [
+                        {"name": k, "dependencies": v} for k, v in features_dict.items()
+                    ]
+
+                # Repository info and GitHub stars
+                repo = crate_data.get("repository", "")
+                gh_stars = 0
+
+                # Check if it's a GitHub repo
+                if "github.com" in repo and self.config.github_token:
+                    match = re.search(r"github.com/([^/]+)/([^/]+)", repo)
+                    if match:
+                        owner, repo_name = match.groups()
+                        repo_name = repo_name.split(".")[0]  # Handle .git extensions
+                        gh_url = f"https://api.github.com/repos/{owner}/{repo_name}"
+                        gh_headers: dict[str, str] = {}
+                        if self.config.github_token:
+                            gh_headers["Authorization"] = (
+                                f"token {self.config.github_token}"
+                            )
+
+                        gh = self.session.get(gh_url, headers=gh_headers)
+                        if gh.ok:
+                            gh_data = gh.json()
+                            gh_stars = gh_data.get("stargazers_count", 0)
+
+                # Check if it's hosted on lib.rs
+                lib_rs_data = {}
+                if "lib.rs" in repo:
+                    lib_rs_url = f"https://lib.rs/crates/{crate_name}"
+                    lib_rs_response = self.session.get(lib_rs_url)
+                    if lib_rs_response.ok:
+                        soup = BeautifulSoup(lib_rs_response.text, "html.parser")
+                        # Get README from lib.rs if not already available
+                        if not readme:
+                            readme_div = soup.find("div", class_="readme")
+                            if readme_div:
+                                readme = readme_div.get_text(
+                                    strip=True
+                                )  # Get lib.rs specific stats
+                        stats_div = soup.find("div", class_="crate-stats")
+                        if isinstance(stats_div, Tag):
+                            downloads_text = stats_div.find(
+                                string=re.compile(r"[\d,]+ downloads")
+                            )
+                            if downloads_text:
+                                lib_rs_data["librs_downloads"] = int(
+                                    re.sub(r"[^\d]", "", str(downloads_text))
+                                )
+
+                # Extract code snippets and sections (simplified)
+                code_snippets: list[str] = (
+                    []
+                )  # Simplified - would normally extract from readme
+                readme_sections: dict[str, str] = (
+                    {}
+                )  # Simplified - would normally parse sections
+
+                result: dict[str, Any] = {
+                    "name": crate_name,
+                    "version": latest,
+                    "description": crate_data.get("description", ""),
+                    "repository": repo,
+                    "keywords": crate_data.get("keywords", []),
+                    "categories": crate_data.get("categories", []),
+                    "readme": readme,
+                    "downloads": crate_data.get("downloads", 0),
+                    "github_stars": gh_stars,
+                    "dependencies": deps,
+                    "code_snippets": code_snippets,
+                    "features": features,
+                    "readme_sections": readme_sections,
+                    **lib_rs_data,
+                }
+
+                return result
+
+        except Exception as e:
+            logging.error(
+                f"Failed fetching metadata for {crate_name}: {str(e)}"
+            )
+            raise
+
+        # If crates.io fails, try lib.rs
+        try:
+            r = self.session.get(f"https://lib.rs/crates/{crate_name}")
+            if r.ok:
+                soup = BeautifulSoup(r.text, "html.parser")
+
+                # Extract metadata from lib.rs page
+                h1 = soup.select_one("h1")
+                name = h1.text.strip() if h1 else crate_name
+
+                # Find description
+                desc_elem = soup.select_one(".description")
+                description = desc_elem.text.strip() if desc_elem else ""
+
+                # Find repository link
+                repo_link: Union[str, None] = None
+                for a in soup.select("a"):
+                    href = a.get("href")
+                    if href and isinstance(href, str) and "github.com" in href:
+                        repo_link = href
+                        break
+
+                # Find keywords
+                keywords_elem = soup.select_one(".keywords")
+                keywords = (
+                    [k.text.strip() for k in keywords_elem.find_all("a")]
+                    if keywords_elem
+                    else []
+                )
+
+                # Basic metadata from lib.rs
+                return {
+                    "name": name,
+                    "version": "latest",  # lib.rs doesn't easily expose version
+                    "description": description,
+                    "repository": repo_link or "",
+                    "keywords": keywords,
+                    "categories": [],
+                    "readme": "",
+                    "downloads": 0,
+                    "github_stars": 0,
+                    "dependencies": [],
+                    "code_snippets": [],
+                    "features": [],
+                    "readme_sections": {},
+                    "source": "lib.rs",
+                }
+        except Exception:
+            pass
+
+        # Finally, try GitHub search
+        try:
+            # This is a simplification - GitHub's search API requires
+            # authentication
+            gh_search_headers: dict[str, str] = {}
+            if self.config.github_token:
+                gh_search_headers["Authorization"] = f"token {self.config.github_token}"
+
+            search_url = (
+                f"https://api.github.com/search/repositories?"
+                f"q={crate_name}+language:rust"
+            )
+            r = requests.get(search_url, headers=gh_search_headers)
+
+            if r.ok:
+                results = r.json().get("items", [])
+                if results:
+                    repo = results[0]  # Take first match
+
+                    # Basic metadata from GitHub
+                    return {
+                        "name": crate_name,
+                        "version": "unknown",
+                        "description": repo.get("description", ""),
+                        "repository": repo.get("html_url", ""),
+                        "keywords": [],
+                        "categories": [],
+                        "readme": "",
+                        "downloads": 0,
+                        "github_stars": repo.get("stargazers_count", 0),
+                        "dependencies": [],
+                        "code_snippets": [],
+                        "features": [],
+                        "readme_sections": {},
+                        "source": "github",
+                    }
+        except Exception:
+            pass
+
+        # If all sources fail
+        return None

rust_crate_pipeline/progress_monitor.py

@@ -0,0 +1,334 @@
+# progress_monitor.py
+"""
+Real-time progress monitoring for the Rust Crate Pipeline (CLI-only).
+
+This module provides:
+- Live progress bars with ETA
+- Real-time statistics and metrics
+- Status printouts
+- Performance monitoring
+- Error tracking and reporting
+- Status JSON file for external tools/scripts
+"""
+
+import time
+import threading
+import json
+import os
+from datetime import datetime, timedelta
+from typing import Dict, List, Optional, Any, Union
+from dataclasses import dataclass, field
+from collections import deque
+import logging
+
+try:
+    from tqdm import tqdm
+    TQDM_AVAILABLE = True
+except ImportError:
+    TQDM_AVAILABLE = False
+
+try:
+    import psutil
+    PSUTIL_AVAILABLE = True
+except ImportError:
+    PSUTIL_AVAILABLE = False
+
+
+@dataclass
+class PipelineMetrics:
+    """Real-time pipeline metrics and statistics."""
+    total_crates: int = 0
+    processed_crates: int = 0
+    successful_crates: int = 0
+    failed_crates: int = 0
+    skipped_crates: int = 0
+    current_batch: int = 0
+    total_batches: int = 0
+    start_time: Optional[datetime] = None
+    current_operation: str = "Initializing"
+    errors: List[Dict[str, Any]] = field(default_factory=list)
+    warnings: List[Dict[str, Any]] = field(default_factory=list)
+    performance_stats: Dict[str, Any] = field(default_factory=dict)
+    
+    @property
+    def progress_percentage(self) -> float:
+        """Calculate progress percentage."""
+        if self.total_crates == 0:
+            return 0.0
+        return (self.processed_crates / self.total_crates) * 100
+    
+    @property
+    def success_rate(self) -> float:
+        """Calculate success rate percentage."""
+        if self.processed_crates == 0:
+            return 0.0
+        return (self.successful_crates / self.processed_crates) * 100
+    
+    @property
+    def elapsed_time(self) -> timedelta:
+        """Calculate elapsed time."""
+        if not self.start_time:
+            return timedelta(0)
+        return datetime.now() - self.start_time
+    
+    @property
+    def estimated_completion(self) -> Optional[datetime]:
+        """Estimate completion time."""
+        if self.processed_crates == 0 or not self.start_time:
+            return None
+        
+        avg_time_per_crate = self.elapsed_time / self.processed_crates
+        remaining_crates = self.total_crates - self.processed_crates
+        estimated_remaining = avg_time_per_crate * remaining_crates
+        
+        return datetime.now() + estimated_remaining
+
+
+class ProgressMonitor:
+    """Real-time progress monitoring with live dashboard."""
+    
+    def __init__(self, total_crates: int, output_dir: str = "output"):
+        self.metrics = PipelineMetrics(total_crates=total_crates)
+        self.output_dir = output_dir
+        self.logger = logging.getLogger(__name__)
+        
+        # Performance tracking
+        self.crate_times: deque = deque(maxlen=100)  # Last 100 crate processing times
+        self.batch_times: deque = deque(maxlen=50)   # Last 50 batch processing times
+        
+        # Status tracking
+        self.current_crate: Optional[str] = None
+        self.current_operation: str = "Initializing"
+        self.status_file = os.path.join(output_dir, "pipeline_status.json")
+        
+        # Thread safety
+        self._lock = threading.Lock()
+        
+        # Initialize
+        self.metrics.start_time = datetime.now()
+        self._save_status()
+        
+        # Create output directory if it doesn't exist
+        os.makedirs(output_dir, exist_ok=True)
+    
+    def start_crate(self, crate_name: str) -> None:
+        """Mark the start of processing a crate."""
+        with self._lock:
+            self.current_crate = crate_name
+            self.current_operation = f"Processing {crate_name}"
+            self.metrics.current_operation = self.current_operation
+            self._save_status()
+    
+    def complete_crate(self, crate_name: str, success: bool = True, 
+                      processing_time: Optional[float] = None) -> None:
+        """Mark the completion of processing a crate."""
+        with self._lock:
+            self.metrics.processed_crates += 1
+            
+            if success:
+                self.metrics.successful_crates += 1
+            else:
+                self.metrics.failed_crates += 1
+            
+            if processing_time:
+                self.crate_times.append(processing_time)
+            
+            self.current_crate = None
+            self.current_operation = "Waiting for next crate"
+            self.metrics.current_operation = self.current_operation
+            
+            # Update performance stats
+            self._update_performance_stats()
+            self._save_status()
+    
+    def skip_crate(self, crate_name: str, reason: str = "Unknown") -> None:
+        """Mark a crate as skipped."""
+        with self._lock:
+            self.metrics.processed_crates += 1
+            self.metrics.skipped_crates += 1
+            
+            self.metrics.warnings.append({
+                "crate": crate_name,
+                "reason": reason,
+                "timestamp": datetime.now().isoformat()
+            })
+            
+            self._save_status()
+    
+    def start_batch(self, batch_num: int, batch_size: int) -> None:
+        """Mark the start of processing a batch."""
+        with self._lock:
+            self.metrics.current_batch = batch_num
+            self.current_operation = f"Processing batch {batch_num}"
+            self.metrics.current_operation = self.current_operation
+            self._save_status()
+    
+    def complete_batch(self, batch_num: int, processing_time: Optional[float] = None) -> None:
+        """Mark the completion of processing a batch."""
+        with self._lock:
+            if processing_time:
+                self.batch_times.append(processing_time)
+            
+            self.current_operation = "Batch completed, preparing next batch"
+            self.metrics.current_operation = self.current_operation
+            self._save_status()
+    
+    def add_error(self, crate_name: str, error: str, error_type: str = "Processing") -> None:
+        """Add an error to the metrics."""
+        with self._lock:
+            self.metrics.errors.append({
+                "crate": crate_name,
+                "error": error,
+                "type": error_type,
+                "timestamp": datetime.now().isoformat()
+            })
+            self._save_status()
+    
+    def add_warning(self, crate_name: str, warning: str) -> None:
+        """Add a warning to the metrics."""
+        with self._lock:
+            self.metrics.warnings.append({
+                "crate": crate_name,
+                "warning": warning,
+                "timestamp": datetime.now().isoformat()
+            })
+            self._save_status()
+    
+    def update_operation(self, operation: str) -> None:
+        """Update the current operation description."""
+        with self._lock:
+            self.current_operation = operation
+            self.metrics.current_operation = operation
+            self._save_status()
+    
+    def _update_performance_stats(self) -> None:
+        """Update performance statistics."""
+        if self.crate_times:
+            self.metrics.performance_stats.update({
+                "avg_crate_time": sum(self.crate_times) / len(self.crate_times),
+                "min_crate_time": min(self.crate_times),
+                "max_crate_time": max(self.crate_times),
+                "crates_per_minute": len(self.crate_times) / (sum(self.crate_times) / 60)
+            })
+        
+        if self.batch_times:
+            self.metrics.performance_stats.update({
+                "avg_batch_time": sum(self.batch_times) / len(self.batch_times),
+                "min_batch_time": min(self.batch_times),
+                "max_batch_time": max(self.batch_times)
+            })
+        
+        # System stats if available
+        if PSUTIL_AVAILABLE:
+            try:
+                cpu_percent = psutil.cpu_percent()
+                memory = psutil.virtual_memory()
+                disk = psutil.disk_usage(self.output_dir)
+                
+                self.metrics.performance_stats.update({
+                    "system_cpu_percent": cpu_percent,
+                    "system_memory_percent": memory.percent,
+                    "system_disk_percent": disk.percent,
+                    "system_memory_available": memory.available,
+                    "system_disk_free": disk.free
+                })
+            except Exception as e:
+                self.logger.warning(f"Failed to get system stats: {e}")
+    
+    def _save_status(self) -> None:
+        """Save current status to file."""
+        try:
+            status_data = {
+                "metrics": {
+                    "total_crates": self.metrics.total_crates,
+                    "processed_crates": self.metrics.processed_crates,
+                    "successful_crates": self.metrics.successful_crates,
+                    "failed_crates": self.metrics.failed_crates,
+                    "skipped_crates": self.metrics.skipped_crates,
+                    "progress_percentage": self.metrics.progress_percentage,
+                    "success_rate": self.metrics.success_rate,
+                    "current_batch": self.metrics.current_batch,
+                    "total_batches": self.metrics.total_batches,
+                    "start_time": self.metrics.start_time.isoformat() if self.metrics.start_time else None,
+                    "elapsed_time": str(self.metrics.elapsed_time),
+                    "estimated_completion": self.metrics.estimated_completion.isoformat() if self.metrics.estimated_completion else None,
+                    "current_operation": self.metrics.current_operation
+                },
+                "current_crate": self.current_crate,
+                "performance_stats": self.metrics.performance_stats,
+                "errors": self.metrics.errors[-10:],  # Last 10 errors
+                "warnings": self.metrics.warnings[-10:],  # Last 10 warnings
+                "last_updated": datetime.now().isoformat()
+            }
+            
+            with open(self.status_file, 'w') as f:
+                json.dump(status_data, f, indent=2)
+                
+        except Exception as e:
+            self.logger.error(f"Failed to save status: {e}")
+    
+    def get_status_summary(self) -> Dict[str, Any]:
+        """Get a summary of current status."""
+        with self._lock:
+            return {
+                "progress": f"{self.metrics.progress_percentage:.1f}%",
+                "processed": f"{self.metrics.processed_crates}/{self.metrics.total_crates}",
+                "success_rate": f"{self.metrics.success_rate:.1f}%",
+                "elapsed_time": str(self.metrics.elapsed_time),
+                "estimated_completion": self.metrics.estimated_completion.isoformat() if self.metrics.estimated_completion else None,
+                "current_operation": self.current_operation,
+                "current_crate": self.current_crate,
+                "errors_count": len(self.metrics.errors),
+                "warnings_count": len(self.metrics.warnings)
+            }
+    
+    def print_status(self) -> None:
+        """Print current status to console."""
+        summary = self.get_status_summary()
+        
+        print("\n" + "="*80)
+        print("🚀 RUST CRATE PIPELINE - REAL-TIME STATUS")
+        print("="*80)
+        print(f"📊 Progress: {summary['progress']} ({summary['processed']} crates)")
+        print(f"✅ Success Rate: {summary['success_rate']}")
+        print(f"⏱️  Elapsed Time: {summary['elapsed_time']}")
+        if summary['estimated_completion']:
+            print(f"🎯 Estimated Completion: {summary['estimated_completion']}")
+        print(f"🔄 Current Operation: {summary['current_operation']}")
+        if summary['current_crate']:
+            print(f"📦 Current Crate: {summary['current_crate']}")
+        print(f"❌ Errors: {summary['errors_count']}")
+        print(f"⚠️  Warnings: {summary['warnings_count']}")
+        
+        # Performance stats
+        if self.metrics.performance_stats:
+            stats = self.metrics.performance_stats
+            if 'avg_crate_time' in stats:
+                print(f"⚡ Avg Crate Time: {stats['avg_crate_time']:.2f}s")
+            if 'crates_per_minute' in stats:
+                print(f"🚀 Processing Rate: {stats['crates_per_minute']:.1f} crates/min")
+            if 'system_cpu_percent' in stats:
+                print(f"💻 System CPU: {stats['system_cpu_percent']:.1f}%")
+            if 'system_memory_percent' in stats:
+                print(f"🧠 System Memory: {stats['system_memory_percent']:.1f}%")
+        
+        print("="*80)
+    
+    def create_progress_bar(self, desc: str = "Processing crates") -> Optional[Any]:
+        """Create a progress bar if tqdm is available."""
+        if not TQDM_AVAILABLE:
+            return None
+        
+        return tqdm(
+            total=self.metrics.total_crates,
+            desc=desc,
+            unit="crate",
+            bar_format="{l_bar}{bar}| {n_fmt}/{total_fmt} [{elapsed}<{remaining}, {rate_fmt}]"
+        )
+
+
+def create_monitor(total_crates: int, output_dir: str = "output") -> ProgressMonitor:
+    """Create and configure a CLI-only progress monitor."""
+    monitor = ProgressMonitor(total_crates, output_dir)
+    print("✅ Real-time CLI progress monitoring enabled")
+    return monitor 

rust_crate_pipeline/version.py

@@ -1,74 +1,74 @@
-from typing import Dict, List, Tuple, Optional, Any
-"""Version information for rust-crate-pipeline."""
-
-__version__ = "1.3.2"
-__version_info__ = tuple(int(x) for x in __version__.split("-")[0].split("."))
-
-# Version history
-# 1.2.5-dev.20250621 - Dev branch: experimental, not a formal
-# release. Originated from v1.2.5.
-# 1.2.5 - Last official release.
-# 1.5.1 - Configuration Standardization Release: Model Path Consistency
-#         - Standardized all configuration to use GGUF model paths
-#         - Updated CLI defaults for --crawl4ai-model to
-#           ~/models/deepseek/deepseek-coder-6.7b-instruct.Q4_K_M.gguf
-#         - Enhanced Rule Zero alignment with transparent configuration practices
-#         - Updated all test files to use consistent GGUF model path references
-#         - Comprehensive documentation updates for proper model configuration
-#         - Removed inconsistent Ollama references in favor of llama-cpp-python
-#         - Ensured CLI help text and JSON examples reflect correct model paths
-# 1.5.0 - Major Release: Enhanced Web Scraping with Crawl4AI Integration
-#         - Integrated Crawl4AI for advanced web scraping capabilities
-#         - Added JavaScript-rendered content extraction via Playwright
-#         - Enhanced README parsing with LLM-powered content analysis
-#         - New CLI options: --enable-crawl4ai, --disable-crawl4ai, --crawl4ai-model
-#         - Enhanced configuration with local GGUF model paths and crawl4ai_timeout
-#         - Comprehensive test coverage for all Crawl4AI features
-#         - Rule Zero compliant with full transparency and audit trails
-# 1.4.0 - Major Release: Rule Zero Compliance Audit Complete
-#         - Completed comprehensive Rule Zero alignment audit
-#         - Eliminated all code redundancy and dead code
-#         - Achieved 100% test coverage (22/22 tests passing)
-#         - Refactored to pure asyncio architecture (thread-free)
-#         - Suppressed Pydantic deprecation warnings
-#         - Full production readiness with Docker support
-#         - Enhanced documentation with PyPI cross-references
-#         - Certified Rule Zero compliance across all four principles
-# 1.3.1 - Bug Fix Release: Crawl4AI Integration Cleanup
-#         - Fixed CSS selector syntax errors in Crawl4AI integration
-#         - Cleaned up duplicate and obsolete test files
-#         - Resolved import conflicts between workspace and integration configs
-#         - Improved error handling in enhanced scraping module
-#         - Standardized on direct llama.cpp approach (removed Ollama dependencies)
-#         - Enhanced Rule Zero compliance with transparent cleanup process
-#         - Fixed type annotation compatibility issues
-#         - Fixed Python 3.9 compatibility for type annotations
-#         - Updated dict[str, Any] to "dict[str, Any]" format
-#         - Fixed Union type expressions in conditional imports
-#         - Resolved IDE linter errors in network.py, pipeline.py, and production_config.py
-#         - Improved code quality and maintainability
-# 1.3.0 - Quality & Integration Release: Comprehensive code quality improvements
-#         - Fixed all critical PEP 8 violations (F821, F811, E114)
-#         - Enhanced error handling with graceful dependency fallbacks
-#         - Improved module integration and import path resolution
-#         - Added comprehensive test validation (21/21 tests passing)
-#         - Enhanced async support and Unicode handling
-#         - Production-ready CLI interfaces with robust error handling
-#         - Full Rule Zero compliance validation
-# 1.2.0 - Major release: Production-ready, cleaned codebase
-#         - Unified documentation into single comprehensive README
-#         - Removed all non-essential development and test files
-#         - Optimized for PyPI distribution and Docker deployment
-#         - Enhanced GitHub token integration and setup
-# 1.1.2 - Production release: Cleaned up non-essential files
-#         - Unified documentation into single README
-#         - Optimized for PyPI distribution
-# 1.1.1 - Bug fix: Added missing python-dateutil dependency
-#         - Fixed relativedelta import error
-# 1.1.0 - Updated author and contact information
-#         - Enhanced package configuration
-# 0.1.0 - Initial release
-#         - Core pipeline functionality
-#         - AI-powered metadata enrichment
-#         - Dependency analysis
-#         - PyPI package setup
+from typing import Dict, List, Tuple, Optional, Any
+"""Version information for rust-crate-pipeline."""
+
+__version__ = "1.3.3"
+__version_info__ = tuple(int(x) for x in __version__.split("-")[0].split("."))
+
+# Version history
+# 1.2.5-dev.20250621 - Dev branch: experimental, not a formal
+# release. Originated from v1.2.5.
+# 1.2.5 - Last official release.
+# 1.5.1 - Configuration Standardization Release: Model Path Consistency
+#         - Standardized all configuration to use GGUF model paths
+#         - Updated CLI defaults for --crawl4ai-model to
+#           ~/models/deepseek/deepseek-coder-6.7b-instruct.Q4_K_M.gguf
+#         - Enhanced Rule Zero alignment with transparent configuration practices
+#         - Updated all test files to use consistent GGUF model path references
+#         - Comprehensive documentation updates for proper model configuration
+#         - Removed inconsistent Ollama references in favor of llama-cpp-python
+#         - Ensured CLI help text and JSON examples reflect correct model paths
+# 1.5.0 - Major Release: Enhanced Web Scraping with Crawl4AI Integration
+#         - Integrated Crawl4AI for advanced web scraping capabilities
+#         - Added JavaScript-rendered content extraction via Playwright
+#         - Enhanced README parsing with LLM-powered content analysis
+#         - New CLI options: --enable-crawl4ai, --disable-crawl4ai, --crawl4ai-model
+#         - Enhanced configuration with local GGUF model paths and crawl4ai_timeout
+#         - Comprehensive test coverage for all Crawl4AI features
+#         - Rule Zero compliant with full transparency and audit trails
+# 1.4.0 - Major Release: Rule Zero Compliance Audit Complete
+#         - Completed comprehensive Rule Zero alignment audit
+#         - Eliminated all code redundancy and dead code
+#         - Achieved 100% test coverage (22/22 tests passing)
+#         - Refactored to pure asyncio architecture (thread-free)
+#         - Suppressed Pydantic deprecation warnings
+#         - Full production readiness with Docker support
+#         - Enhanced documentation with PyPI cross-references
+#         - Certified Rule Zero compliance across all four principles
+# 1.3.1 - Bug Fix Release: Crawl4AI Integration Cleanup
+#         - Fixed CSS selector syntax errors in Crawl4AI integration
+#         - Cleaned up duplicate and obsolete test files
+#         - Resolved import conflicts between workspace and integration configs
+#         - Improved error handling in enhanced scraping module
+#         - Standardized on direct llama.cpp approach (removed Ollama dependencies)
+#         - Enhanced Rule Zero compliance with transparent cleanup process
+#         - Fixed type annotation compatibility issues
+#         - Fixed Python 3.9 compatibility for type annotations
+#         - Updated dict[str, Any] to "dict[str, Any]" format
+#         - Fixed Union type expressions in conditional imports
+#         - Resolved IDE linter errors in network.py, pipeline.py, and production_config.py
+#         - Improved code quality and maintainability
+# 1.3.0 - Quality & Integration Release: Comprehensive code quality improvements
+#         - Fixed all critical PEP 8 violations (F821, F811, E114)
+#         - Enhanced error handling with graceful dependency fallbacks
+#         - Improved module integration and import path resolution
+#         - Added comprehensive test validation (21/21 tests passing)
+#         - Enhanced async support and Unicode handling
+#         - Production-ready CLI interfaces with robust error handling
+#         - Full Rule Zero compliance validation
+# 1.2.0 - Major release: Production-ready, cleaned codebase
+#         - Unified documentation into single comprehensive README
+#         - Removed all non-essential development and test files
+#         - Optimized for PyPI distribution and Docker deployment
+#         - Enhanced GitHub token integration and setup
+# 1.1.2 - Production release: Cleaned up non-essential files
+#         - Unified documentation into single README
+#         - Optimized for PyPI distribution
+# 1.1.1 - Bug fix: Added missing python-dateutil dependency
+#         - Fixed relativedelta import error
+# 1.1.0 - Updated author and contact information
+#         - Enhanced package configuration
+# 0.1.0 - Initial release
+#         - Core pipeline functionality
+#         - AI-powered metadata enrichment
+#         - Dependency analysis
+#         - PyPI package setup

{rust_crate_pipeline-1.3.2.dist-info → rust_crate_pipeline-1.3.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rust-crate-pipeline
-Version: 1.3.2
+Version: 1.3.3
 Summary: A comprehensive system for gathering, enriching, and analyzing metadata for Rust crates using AI-powered insights
 Home-page: https://github.com/Superuser666-Sigil/SigilDERG-Data_Production
 Author: SuperUser666-Sigil

{rust_crate_pipeline-1.3.2.dist-info → rust_crate_pipeline-1.3.3.dist-info}/RECORD

@@ -8,12 +8,13 @@ rust_crate_pipeline/crate_analysis.py,sha256=GsoXemJ9VFyAbb4Sm5gY5ToTqNtOA4pI38A
 rust_crate_pipeline/crate_list.txt,sha256=W3NxDtxvihyKp9SN85FYXX6p8Hh49IFih1M4-c-CynM,4334
 rust_crate_pipeline/github_token_checker.py,sha256=COXXS9uoLV9WYIcT02C-bV5uH3fa9D9HJImc07vMjLs,3766
 rust_crate_pipeline/main.py,sha256=iGYEAYvXkoFFvaA6DIVGiUL3wLhiCzatB6Fvf-Yrj2A,18858
-rust_crate_pipeline/network.py,sha256=SSSolG5QdK4m9E77Ko3m-8DM1xz1Ha9XP9yeLSCfuaU,13308
+rust_crate_pipeline/network.py,sha256=khyjfOplaDvMxLWGB-JbPQnc27ZfozKGYBFw2b3BScM,12834
 rust_crate_pipeline/pipeline.py,sha256=YN6PEhg0Si_oo6-Wtm_PviytzWzpQupTPC2e4L1F7XE,16349
 rust_crate_pipeline/production_config.py,sha256=uWylP9AIZZx7-9aT4sFmAKEEW9miJDxaiek8VE6WP-0,2372
+rust_crate_pipeline/progress_monitor.py,sha256=5K9KP-Xggi1JEINfRmq2W-wGUHtNIBTcocpDtB1t8iM,13743
 rust_crate_pipeline/unified_llm_processor.py,sha256=eo7KotNuqwc7_hgpFm18QLokFoufFslnvi8TnDsSYEg,25064
 rust_crate_pipeline/unified_pipeline.py,sha256=2yglmXVlQfSkVq0HVTPonDee6VxWaQWZw0X2l4lLBGw,23704
-rust_crate_pipeline/version.py,sha256=f9QzOtJjGR2-83eFezB55H6KgfM0Gi5XAPOooI5Y5_M,4489
+rust_crate_pipeline/version.py,sha256=rvOvTXgn4ikcVgnUnkRQ9jMb3vGNh_UC85DLNgzLELw,4415
 rust_crate_pipeline/core/__init__.py,sha256=Sq4HWdANGqoYln7JdCog7m3BsGeR3tHdseeflvNetoQ,509
 rust_crate_pipeline/core/canon_registry.py,sha256=36tmt_wU6-kSyZnGfh53N64C7E3G-QR7GFbr9epj4zg,4700
 rust_crate_pipeline/core/irl_engine.py,sha256=QRZUdkN24W9XutLkj8JDplEz6FmnquUrwKsl0s2zRr4,10491
@@ -22,9 +23,9 @@ rust_crate_pipeline/scraping/__init__.py,sha256=ySkTRg7nIxgcbHJQ3L1XzcrOo281NZu0
 rust_crate_pipeline/scraping/unified_scraper.py,sha256=ZE2gkc0vQ3BOLdSX_IV-kMe8QAm2Av4M7VqpkxEKyT4,9965
 rust_crate_pipeline/utils/file_utils.py,sha256=tMaCPy7ghs9x4Hxu_sviX8MXU2sBjNvohUrvt4MejoM,2853
 rust_crate_pipeline/utils/logging_utils.py,sha256=e5jG0Yd6k3exgAdbVca46kWADJ_Qz8UJ3yEJzwTqPyI,2452
-rust_crate_pipeline-1.3.2.dist-info/licenses/LICENSE,sha256=tpd4XNpbssrSx9-iErATOLrOh0ivNPfO2I5MAPUpats,1088
-rust_crate_pipeline-1.3.2.dist-info/METADATA,sha256=sMYLvaOvjRgZNP1iHuNb0NEWxgqY_uqzdx_PGnWtMT0,11254
-rust_crate_pipeline-1.3.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rust_crate_pipeline-1.3.2.dist-info/entry_points.txt,sha256=9Rr_IRuFRIridXxUSdEJbB3ba0NnpEfKmknZXFdYRC0,70
-rust_crate_pipeline-1.3.2.dist-info/top_level.txt,sha256=GUdB7RyxHLhijQxui_KTy3B8p_L2APui9C6RYa0FuaE,20
-rust_crate_pipeline-1.3.2.dist-info/RECORD,,
+rust_crate_pipeline-1.3.3.dist-info/licenses/LICENSE,sha256=tpd4XNpbssrSx9-iErATOLrOh0ivNPfO2I5MAPUpats,1088
+rust_crate_pipeline-1.3.3.dist-info/METADATA,sha256=71onHncBIIY4LaCuTT6soQPoMdROFUkvFZwHYd4Tbe4,11254
+rust_crate_pipeline-1.3.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rust_crate_pipeline-1.3.3.dist-info/entry_points.txt,sha256=9Rr_IRuFRIridXxUSdEJbB3ba0NnpEfKmknZXFdYRC0,70
+rust_crate_pipeline-1.3.3.dist-info/top_level.txt,sha256=GUdB7RyxHLhijQxui_KTy3B8p_L2APui9C6RYa0FuaE,20
+rust_crate_pipeline-1.3.3.dist-info/RECORD,,