Python: Add non-alert data for extractor diagnostics

This is basically just a port of the C++/JS queries added in:

- https://github.com/github/codeql/pull/5414 (C++)
- https://github.com/github/codeql/pull/5656 (JS)

SyntaxError should capture all errors we have information about. At least in
`python/ql/src/semmlecode.python.dbscheme` the only match for `error` is
`py_syntax_error_versioned` (which `SyntaxError` is based on).

python/ql/src/Diagnostics/ExtractionErrors.ql

@@ -0,0 +1,23 @@
+/**
+ * @name Python extraction errors
+ * @description List all extraction errors for Python files in the source code directory.
+ * @kind diagnostic
+ * @id py/diagnostics/extraction-errors
+ */
+
+import python
+
+/**
+ * Gets the SARIF severity for errors.
+ *
+ * See point 3.27.10 in https://docs.oasis-open.org/sarif/sarif/v2.0/sarif-v2.0.html for
+ * what error means.
+ */
+int getErrorSeverity() { result = 2 }
+
+from SyntaxError error, File file
+where
+  file = error.getFile() and
+  exists(file.getRelativePath())
+select error, "Extraction failed in " + file + " with error " + error.getMessage(),
+  getErrorSeverity()

python/ql/src/Diagnostics/SuccessfullyExtractedFiles.ql

@@ -0,0 +1,15 @@
+/**
+ * @name Successfully extracted Python files
+ * @description Lists all Python files in the source code directory that were extracted
+ *   without encountering an error.
+ * @kind diagnostic
+ * @id py/diagnostics/successfully-extracted-files
+ */
+
+import python
+
+from File file
+where
+  not exists(SyntaxError e | e.getFile() = file) and
+  exists(file.getRelativePath())
+select file, ""

python/ql/test/query-tests/Diagnostics/ExtractionErrors.expected

@@ -0,0 +1,2 @@
+| bad_encoding.py:2:11:2:11 | Encoding Error | Extraction failed in bad_encoding.py with error 'utf-8' codec can't decode byte 0x9d in position 88: invalid start byte | 2 |
+| syntax_error.py:1:31:1:31 | Syntax Error | Extraction failed in syntax_error.py with error Syntax Error | 2 |

python/ql/test/query-tests/Diagnostics/ExtractionErrors.qlref

@@ -0,0 +1 @@
+Diagnostics/ExtractionErrors.ql

python/ql/test/query-tests/Diagnostics/SuccessfullyExtractedFiles.expected

@@ -0,0 +1 @@
+| good_file.py:0:0:0:0 | good_file.py |  |

python/ql/test/query-tests/Diagnostics/SuccessfullyExtractedFiles.qlref

@@ -0,0 +1 @@
+Diagnostics/SuccessfullyExtractedFiles.ql

python/ql/test/query-tests/Diagnostics/bad_encoding.py

@@ -0,0 +1,2 @@
+# Note: This file has been encoded in Windows 1252 to provoke encoding error
+print("wat<EFBFBD>")

python/ql/test/query-tests/Diagnostics/good_file.py

@@ -0,0 +1 @@
+print("hello world")

python/ql/test/query-tests/Diagnostics/syntax_error.py

@@ -0,0 +1 @@
+print("no closing parenthesis"