Standardisation 9

Readme.org

@@ -174,6 +174,7 @@ scripts migrés vers cette convention sont actuellement :
 - =page_splitter.py=, =cutleft.py=, =plotting.py= et
   =splitting_int.py= ;
 - =gemini_for_labels.py= ;
+- =gemini_for_enonce.py= et =enonce_info.py= ;
 - =correction.py=, =submit_batches.py=, =batch_status.py= et
   =fetch_batched_results.py= ;
 - =annotating.py=, =annotating_with_checks.py= et
@@ -235,6 +236,12 @@ Dans le dossier de l'évaluation, mettre les fichiers suivants de l'évaluation
 
  - Alternative personnelle : `python enonce_info.py Interro`
 
+   Ces deux commandes suivent la convention des scripts standardisés.
+   Leur import ne lance aucun traitement et les erreurs partielles sont
+   distinguées des échecs. Les réponses d'extraction mises en cache par
+   =gemini_for_enonce.py= et le fichier =labels= sont publiés
+   atomiquement.
+
 ** Prétraitement des copies
 
 Mettre les copies scannées au format pdf dans =Interro=.

enonce_info.py

@@ -1,16 +1,26 @@
-import sys
-import os
+from __future__ import annotations
+
+import argparse
 import glob
 import json
-import urllib.request
+import os
 import re
-import subprocess
-import tempfile
-import shutil
+import urllib.request
+from collections.abc import Sequence
+from uuid import uuid4
 
+from copienator import (
+    CliError,
+    EvaluationWorkspace,
+    ExitCode,
+    evaluation_parser,
+    execute,
+    workspace_from_args,
+)
 from platform_utils import WindowsLabelError, validate_windows_labels
 from utils import compile_to_pdf
 
+
 def fetch_and_save_sub_text(ex_id, indices, label, text_path):
     """Fetches text for a specific sub-question and saves it to Text/{label}.tex"""
     qinds = ",".join(map(str, indices))
@@ -29,6 +39,7 @@ def fetch_and_save_sub_text(ex_id, indices, label, text_path):
             compile_to_pdf(content, pdf_file)
     except Exception as e:
         print(f"Error fetching sub-text from {url}: {e}")
+        raise
 
 def fetch_and_save_sub_sol(ex_id, indices, label, sol_path):
     """Fetches text for a specific sub-question and saves it to Text/{label}.tex"""
@@ -48,6 +59,7 @@ def fetch_and_save_sub_sol(ex_id, indices, label, sol_path):
             compile_to_pdf(content, pdf_file)
     except Exception as e:
         print(f"Error fetching sub-text from {url}: {e}")
+        raise
 
 
 ROMANS_CAP = ["", "I", "II", "III", "IV", "V", "VI", "VII", "VIII", "IX", "X"]
@@ -127,18 +139,21 @@ def save_split_content(text, path, base_fname, problem):
             f.write(chunk)
 
 
-def process_directory(directory):
+def process_directory(workspace: EvaluationWorkspace) -> ExitCode:
+    directory = str(workspace.root)
     # Find the first .tex file in the directory
     tex_files = glob.glob(os.path.join(directory, "*.tex"))
     if not tex_files:
         print(f"No .tex file found in {directory}. Looking in /Staging/Interro/")
-        int_name = directory[:-1] if directory.endswith("/") else directory
+        int_name = directory.removesuffix("/")
         tex_path = os.path.join(os.path.expanduser("~"), "Prépa/Staging/Interro", f"{int_name}.tex")
         if os.path.exists(tex_path):
             tex_file = tex_path
         else:
-            print("Not found in ", tex_path)
-            return
+            raise CliError(
+                f"No .tex input found in {workspace.root}",
+                ExitCode.INVALID_WORKSPACE,
+            )
     else:
         tex_file = tex_files[0]
 
@@ -153,8 +168,10 @@ def process_directory(directory):
     for p in paths.values():
         os.makedirs(p, exist_ok=True)
 
-    labels_file = os.path.join(directory, "labels")
+    labels_file = workspace.labels_file
+    labels_staging = labels_file.with_name(f".{labels_file.name}.{uuid4().hex}.tmp")
     current_ex_num = 1
+    had_errors = False
 
     # Read entirely to allow chunking
     with open(tex_file, 'r', encoding='utf-8') as f_in:
@@ -162,8 +179,11 @@ def process_directory(directory):
 
     # Split by the specific SHEETINFO tag
     blocks = content.split("%%SHEETINFO :")
+    if len(blocks) == 1:
+        print(f"No SHEETINFO blocks found in {tex_file}")
+        return ExitCode.PARTIAL
 
-    with open(labels_file, 'w', encoding='utf-8') as f_labels:
+    with open(labels_staging, 'w', encoding='utf-8') as f_labels:
         # Skip blocks[0] (content before first SHEETINFO)
         for block in blocks[1:]:
             parts_line = block.split("\n", 1)
@@ -177,6 +197,7 @@ def process_directory(directory):
 
             try:
                 data = json.loads(json_str)
+                block_labels = []
                 # Construct 'ids' parameter
                 ex_id = str(data['id'])
                 selection = data.get('select')
@@ -193,7 +214,7 @@ def process_directory(directory):
                 if not indexes:
                     label = f"Ex {current_ex_num}"
                     validate_windows_labels([label])
-                    f_labels.write(f"{label}\n")
+                    block_labels.append(label)
                     fetch_and_save_sub_text(ids, [], label, paths['Text2'])
                     fetch_and_save_sub_sol(ids, [], label, paths['Sol2'])
                 else:
@@ -201,7 +222,7 @@ def process_directory(directory):
                         suffix = format_indices(item['indices'], problem)
                         label = f"Ex {current_ex_num}" + (f" : {suffix}" if suffix else "")
                         validate_windows_labels([label])
-                        f_labels.write(f"{label}\n")
+                        block_labels.append(label)
                         fetch_and_save_sub_text(ids, item['indices'], label, paths['Text2'])
                         fetch_and_save_sub_sol(ids, item['indices'], label, paths['Sol2'])
 
@@ -244,18 +265,31 @@ def process_directory(directory):
                 save_split_content(s_text, paths['Sol'], base_filename, problem)
                 save_split_content(p_text, paths['Persp'], base_filename, problem)
 
+                for label in block_labels:
+                    f_labels.write(f"{label}\n")
                 current_ex_num += 1
 
             except WindowsLabelError:
+                labels_staging.unlink(missing_ok=True)
                 raise
             except json.JSONDecodeError:
                 print(f"Error decoding JSON in block: {json_str}")
-            except Exception as e:
+                had_errors = True
+            except Exception as e:  # noqa: BLE001 - one malformed exercise is partial
                 print(f"Error processing block {ex_id if 'ex_id' in locals() else 'unknown'}: {e}")
+                had_errors = True
+
+    labels_staging.replace(labels_file)
+    return ExitCode.PARTIAL if had_errors else ExitCode.SUCCESS
+
+
+def build_parser() -> argparse.ArgumentParser:
+    return evaluation_parser("Generate statement metadata from SHEETINFO blocks")
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    parser = build_parser()
+    return execute(parser, argv, lambda args: process_directory(workspace_from_args(args)))
 
 if __name__ == "__main__":
-    if len(sys.argv) < 2:
-        print("Usage: python script.py <Dir>")
-        sys.exit(1)
-
-    process_directory(sys.argv[1])
+    raise SystemExit(main())

gemini_for_enonce.py

@@ -1,18 +1,30 @@
-import re
-import os
-import utils
-import subprocess
-import sys
+from __future__ import annotations
+
 import argparse
+import re
+from collections.abc import Sequence
+from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
-from pydantic import BaseModel, Field
-from typing import List, Union
+
 from google import genai
 from google.genai import types
-from concurrent.futures import ThreadPoolExecutor
+from pydantic import BaseModel, Field
+
+import config
+import utils
+from copienator import (
+    CliError,
+    EvaluationWorkspace,
+    ExitCode,
+    atomic_write_text,
+    evaluation_parser,
+    execute,
+    workspace_from_args,
+)
 from platform_utils import validate_windows_labels
 from utils import compile_to_pdf
 
+
 def get_lcp(s1: str, s2: str) -> str:
     i = 0
     while i < len(s1) and i < len(s2) and s1[i] == s2[i]:
@@ -25,8 +37,6 @@ def get_lcp(s1: str, s2: str) -> str:
     return lcp
 
 
-import config
-
 MODEL_ID = config.MODEL_LITE_ID
 api_key = config.API_KEY
 
@@ -36,7 +46,7 @@ class QuestionOnlyItem(BaseModel):
     question_content: str = Field(description="The source text of the question, strictly extracted from the enonce file, EXCLUDING the label itself.")
 
 class ExamQuestions(BaseModel):
-    questions: List[QuestionOnlyItem]
+    questions: list[QuestionOnlyItem]
 
 # --- Modèles pour la Requête 2 ---
 class SolutionOnlyItem(BaseModel):
@@ -44,7 +54,7 @@ class SolutionOnlyItem(BaseModel):
     solution_content: str = Field(description="The source text of the solution, strictly extracted from the correction file.")
 
 class ExamSolutions(BaseModel):
-    solutions: List[SolutionOnlyItem]
+    solutions: list[SolutionOnlyItem]
 
 # --- Modèles pour la Requête 3 ---
 class ExtractedContext(BaseModel):
@@ -53,7 +63,7 @@ class ExtractedContext(BaseModel):
     context_content: str = Field(description="The source text of the definitions, notations, or hypotheses, extracted from the enonce.")
 
 class ExamContext(BaseModel):
-    contexts: List[ExtractedContext]
+    contexts: list[ExtractedContext]
 
 # --- Modèles pour la Requête 4 (Barèmes) ---
 class RubricItem(BaseModel):
@@ -61,7 +71,7 @@ class RubricItem(BaseModel):
     rubric_content: str = Field(description="Le barème détaillé en français.")
 
 class GroupRubrics(BaseModel):
-    rubrics: List[RubricItem]
+    rubrics: list[RubricItem]
 
 PROMPT_4 = """Je te fournis les questions, le contexte éventuel, et les corrections pour un groupe de questions d'un examen.
 Ta tâche :
@@ -87,10 +97,10 @@ class ContextItem(BaseModel):
     content: str  # Juste une string encapsulée pour le différencier facilement
 
 class ExamExtraction(BaseModel):
-    items: List[Union[QuestionItem, ContextItem]] # Liste mixte
+    items: list[QuestionItem | ContextItem] # Liste mixte
 
 class GroupedExamExtraction(BaseModel):
-    groups: List[List[Union[QuestionItem, ContextItem]]]
+    groups: list[list[QuestionItem | ContextItem]]
 
 PROMPT_1 = """I am providing:
 1. A PDF of an exam (`enonce.pdf`)
@@ -138,15 +148,20 @@ the `Let N, M be two commutating matrices` part is not a question itself, and is
  Return the result as a JSON list.
 """
 
-def find_file(folder: Path, base_name: str) -> Path:
+def find_file(folder: Path, base_name: str) -> Path | None:
     for ext in [".org", ".tex"]:
         path = folder / f"{base_name}{ext}"
         if path.is_file():
             return path
     return None
 
-def process_exam(folder_path: str, restart: bool = False):
-    folder = Path(folder_path)
+def process_exam(
+    workspace: EvaluationWorkspace,
+    restart: bool = False,
+    *,
+    api_client=None,
+) -> ExitCode:
+    folder = workspace.root
 
     cache_dir = folder / "Cache"
     tmp_dir = folder / "Tmp"
@@ -168,15 +183,21 @@ def process_exam(folder_path: str, restart: bool = False):
     if not correction_path: missing.append("correction.org or correction.tex")
 
     if missing:
-        print(f"Error: Missing files in {folder}: {', '.join(missing)}")
-        sys.exit(1)
+        raise CliError(
+            f"Missing files in {folder}: {', '.join(missing)}",
+            ExitCode.INVALID_WORKSPACE,
+        )
 
     print("Reading files...")
     pdf_bytes = pdf_path.read_bytes()
     enonce_text = enonce_path.read_text(encoding="utf-8")
     correction_text = correction_path.read_text(encoding="utf-8")
 
-    client = genai.Client(api_key=api_key)
+    if api_client is None:
+        if not api_key:
+            raise CliError("GEMINI_API_KEY is not configured")
+        api_client = genai.Client(api_key=api_key)
+    client = api_client
 
     # ==========================================
     # REQUÊTE 1 : Extraction des Énoncés
@@ -210,7 +231,7 @@ def process_exam(folder_path: str, restart: bool = False):
         )
         response_q_text = response_q.text
         print("Saving questions to cache...")
-        cache_q_file.write_text(response_q_text, encoding="utf-8")
+        atomic_write_text(cache_q_file, response_q_text)
 
     questions_data = ExamQuestions.model_validate_json(response_q_text)
 
@@ -248,7 +269,7 @@ def process_exam(folder_path: str, restart: bool = False):
         )
         response_s_text = response_s.text
         print("Saving solutions to cache...")
-        cache_s_file.write_text(response_s_text, encoding="utf-8")
+        atomic_write_text(cache_s_file, response_s_text)
 
     solutions_data = ExamSolutions.model_validate_json(response_s_text)
 
@@ -284,7 +305,7 @@ def process_exam(folder_path: str, restart: bool = False):
         )
         response_c_text = response_c.text
         print("Saving context to cache...")
-        cache_c_file.write_text(response_c_text, encoding="utf-8")
+        atomic_write_text(cache_c_file, response_c_text)
 
     context_data = ExamContext.model_validate_json(response_c_text)
 
@@ -388,7 +409,6 @@ def process_exam(folder_path: str, restart: bool = False):
     for g_indices in q_group_indices:
         group_items = []
         first_q_idx = g_indices[0]
-        last_q_idx = g_indices[-1]
 
         for q_idx in g_indices:
             q_item = questions_only[q_idx]
@@ -497,14 +517,13 @@ def process_exam(folder_path: str, restart: bool = False):
 
         # 2. Actual Parsing
         grouped_items = []
-        current_raw_group = []  # Stores (is_context, label_or_flag, content)
         all_new_q_labels = []
 
         # Pass 1: Read all edited lines and collect question labels in sequence
         for line in edited_lines:
             if line == "---" or " ### " not in line:
                 continue
-            lbl, content_raw = line.split(" ### ", 1)
+            lbl, _content_raw = line.split(" ### ", 1)
             lbl = lbl.strip()
             if lbl != "CONTEXT":
                 all_new_q_labels.append(lbl)
@@ -606,10 +625,6 @@ def process_exam(folder_path: str, restart: bool = False):
     validate_windows_labels(labels_list)
 
     # Save labels and proceed
-    with open(folder / "labels", 'w', encoding='utf-8') as f_labels:
-        for label in labels_list:
-            f_labels.write(f"{label}\n")
-
     grouped_extraction = GroupedExamExtraction(groups=grouped_items)
 
     # 2. Setup output directories
@@ -628,8 +643,7 @@ def process_exam(folder_path: str, restart: bool = False):
         ).strip().lower()
 
         if answer not in ("y", "yes"):
-            print("Aborted.")
-            sys.exit(1)
+            raise CliError("Output replacement aborted", ExitCode.INVALID_ARGUMENTS)
         # Empty each directory
         for d in dirs:
             if d.exists():
@@ -645,6 +659,7 @@ def process_exam(folder_path: str, restart: bool = False):
 
 
     print("Writing grouped question and solution files...")
+    processing_errors = []
 
     for group in grouped_extraction.groups:
         q_items = [item for item in group if isinstance(item, QuestionItem)]
@@ -690,8 +705,9 @@ def process_exam(folder_path: str, restart: bool = False):
             )
             rubrics_data = GroupRubrics.model_validate_json(response_r.text)
             rubrics_map = {r.label: r.rubric_content for r in rubrics_data.rubrics}
-        except Exception as e:
+        except Exception as e:  # noqa: BLE001 - remote API boundary
             print(f"Error generating rubric for group {labels[0]}: {e}")
+            processing_errors.append(str(e))
             rubrics_map = {}
 
         # 1. Compute the common prefix for the group
@@ -737,7 +753,7 @@ def process_exam(folder_path: str, restart: bool = False):
             elif isinstance(item, ContextItem):
                 raw_ctx = item.content.strip()
                 tabulated_ctx = "\t" + re.sub(r'\n\s*', '\n\t', raw_ctx)
-                text_content_lines.append(f"CONTEXT :")
+                text_content_lines.append("CONTEXT :")
                 text_content_lines.append(tabulated_ctx)
 
                 # --- Save context to Text2 (Concatenating if exists) ---
@@ -762,29 +778,53 @@ def process_exam(folder_path: str, restart: bool = False):
     # ==========================================
     all_tex_files = list(text2_dir.glob("*.tex")) + list(sol2_dir.glob("*.tex"))
 
-    def compile_worker(tex_file: Path):
+    def compile_worker(tex_file: Path) -> str | None:
         """Helper to read content and call the utility function."""
         try:
             content = tex_file.read_text(encoding="utf-8")
             pdf_path = tex_file.with_suffix(".pdf")
             compile_to_pdf(content, pdf_path)
-        except Exception as e:
-            print(f"Error compiling {tex_file.name}: {e}")
+        except Exception as e:  # noqa: BLE001 - compiler worker boundary
+            return f"Error compiling {tex_file.name}: {e}"
+        return None
 
     print(f"Compiling {len(all_tex_files)} files to PDF using 4 threads...")
     with ThreadPoolExecutor(max_workers=4) as executor:
-        executor.map(compile_worker, all_tex_files)
+        compile_errors = [
+            error for error in executor.map(compile_worker, all_tex_files) if error
+        ]
+    for error in compile_errors:
+        print(error)
+    processing_errors.extend(compile_errors)
+    atomic_write_text(
+        workspace.labels_file,
+        "".join(f"{label}\n" for label in labels_list),
+    )
+
+    return ExitCode.PARTIAL if processing_errors else ExitCode.SUCCESS
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = evaluation_parser("Extract exam and solution code via Gemini")
+    parser.add_argument(
+        "--restart",
+        action="store_true",
+        help="Ignore cached Gemini extraction responses",
+    )
+    return parser
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    parser = build_parser()
+    return execute(
+        parser,
+        argv,
+        lambda args: process_exam(
+            workspace_from_args(args),
+            restart=args.restart,
+        ),
+    )
 
 
 if __name__ == "__main__":
-    if not api_key:
-        print("Error: GEMINI_API_KEY environment variable is not set.")
-        sys.exit(1)
-
-    parser = argparse.ArgumentParser(description="Extract exam and solution code via Gemini.")
-    parser.add_argument("folder", help="Directory containing the exam files")
-    parser.add_argument("--restart", action="store_true", help="Ignore cache files and re-run extraction requests.")
-
-
-    args = parser.parse_args()
-    process_exam(args.folder, restart=args.restart)
+    raise SystemExit(main())

tests/test_gui_core.py

@@ -322,6 +322,10 @@ class StandardCliTests(unittest.TestCase):
             "gemini_for_labels": load_script_module(
                 "gemini_for_labels.py", "gemini_for_labels"
             ),
+            "gemini_for_enonce": load_script_module(
+                "gemini_for_enonce.py", "gemini_for_enonce"
+            ),
+            "enonce_info": load_script_module("enonce_info.py", "enonce_info"),
             "correction": load_script_module("correction.py", "correction"),
             "submit_batches": load_script_module(
                 "submit_batches.py", "submit_batches"
@@ -372,6 +376,8 @@ class StandardCliTests(unittest.TestCase):
                 "page_splitter": [missing],
                 "plotting": [missing],
                 "gemini_for_labels": [missing],
+                "gemini_for_enonce": [missing],
+                "enonce_info": [missing],
                 "correction": [missing],
                 "submit_batches": [missing],
                 "fetch_batched_results": [missing],
@@ -419,6 +425,16 @@ class StandardCliTests(unittest.TestCase):
         steps = {step.id: step for step in build_workflow(True)}
         evaluation = "Evaluation with spaces"
         cases = {
+            "gemini_for_enonce": (
+                "statement",
+                "gemini",
+                {"target": evaluation, "restart": True},
+            ),
+            "enonce_info": (
+                "statement",
+                "personal",
+                {"target": evaluation},
+            ),
             "export": ("export", "default", {"target": evaluation, "refaire": True}),
             "import": ("import", "default", {"target": evaluation, "refaire": True}),
             "giving_names": (
@@ -534,6 +550,21 @@ class StandardCliTests(unittest.TestCase):
                 self.assertEqual(parsed.operation, step_id)
                 self.assertEqual(str(parsed.evaluation), evaluation)
 
+    def test_enonce_info_preserves_labels_when_no_blocks_are_found(self) -> None:
+        module = self.modules["enonce_info"]
+        with tempfile.TemporaryDirectory() as directory:
+            evaluation = Path(directory) / "Exam"
+            evaluation.mkdir()
+            (evaluation / "source.tex").write_text(
+                "No SHEETINFO blocks\n", encoding="utf-8"
+            )
+            (evaluation / "labels").write_text("Existing\n", encoding="utf-8")
+            self.assertEqual(
+                module.process_directory(EvaluationWorkspace(evaluation)), 4
+            )
+            self.assertEqual((evaluation / "labels").read_text(), "Existing\n")
+            self.assertFalse(list(evaluation.glob(".labels.*.tmp")))
+
     def test_export_main_copies_outputs(self) -> None:
         module = self.modules["export"]
         with tempfile.TemporaryDirectory() as directory: