From 10c8e4f8b405dcb84269cbe0af54dbf4fb6e610d Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Tue, 20 Oct 2020 01:29:22 -0700
Subject: [PATCH] Only create debug.log when running from command line

When used as a library ocrmypdf shouldn't make policy decisions, like where to
put a log file. Unsurprisingly, creating it causes problems for library users
because we deleted the temporary folder which held the log file and made no
effort to move it to a new location.

Also update the documentation to better described how an application should
handle this.

Closes #657
---
 src/ocrmypdf/_sync.py |  7 +++++--
 src/ocrmypdf/api.py   | 32 ++++++++++++++++++++++++--------
 2 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/src/ocrmypdf/_sync.py b/src/ocrmypdf/_sync.py
index 22b9afa8..68c24da5 100644
--- a/src/ocrmypdf/_sync.py
+++ b/src/ocrmypdf/_sync.py
@@ -330,9 +330,12 @@ def run_pipeline(options, *, plugin_manager, api=False):
 
     work_folder = Path(mkdtemp(prefix="com.github.ocrmypdf."))
     debug_log_handler = None
-    if (options.keep_temporary_files or options.verbose >= 1) and not os.environ.get(
-        'PYTEST_CURRENT_TEST', ''
+    if (
+        (options.keep_temporary_files or options.verbose >= 1)
+        and not os.environ.get('PYTEST_CURRENT_TEST', '')
+        and not api
     ):
+        # Debug log for command line interface only with verbose output
         debug_log_handler = configure_debug_logging(Path(work_folder) / "debug.log")
 
     pikepdf_enable_mmap()
diff --git a/src/ocrmypdf/api.py b/src/ocrmypdf/api.py
index 898d9e11..f8809157 100644
--- a/src/ocrmypdf/api.py
+++ b/src/ocrmypdf/api.py
@@ -11,6 +11,7 @@ import sys
 from enum import IntEnum
 from pathlib import Path
 from typing import BinaryIO, Iterable, Union
+from warnings import warn
 
 from ocrmypdf._logging import PageNumberFilter, TqdmConsole
 from ocrmypdf._plugin_manager import get_plugin_manager
@@ -44,16 +45,28 @@ def configure_logging(
 ):
     """Set up logging.
 
-    Library users may wish to use this function if they want their log output to be
-    similar to ocrmypdf command line interface. If not used, the external application
-    should configure logging on its own.
+    Before calling :func:`ocrmypdf.ocr()`, you can use this function to
+    configure logging, if you want ocrmypdf's output to look like the ocrmypdf
+    command line interface. It will register log handlers, log filters, and
+    formatters, configure color logging to standard error, and adjust the log
+    levels of third party libraries. Details of this are fine-tuned and subject
+    to change. The ``verbosity`` argument is equivalent to the argument
+    ``--verbose`` and applies those settings.
 
-    ocrmypdf will perform all of its logging under the ``"ocrmypdf"`` logging namespace.
-    In addition, ocrmypdf imports pdfminer, which logs under ``"pdfminer"``. A library
-    user may wish to configure both; note that pdfminer is extremely chatty at the log
-    level ``logging.INFO``.
+    If this function is not called, ocrmypdf will not configure logging, and it
+    is up to the caller of ``ocrmypdf.ocr()`` to set up logging as it wishes using
+    the Python standard library's logging module. If this function is called,
+    the caller may of course make further adjustments to logging.
 
-    Library users may perform additional configuration afterwards.
+    Regardless of whether this function is called, ocrmypdf will perform all of
+    its logging under the ``"ocrmypdf"`` logging namespace. In addition,
+    ocrmypdf imports pdfminer, which logs under ``"pdfminer"``. A library user
+    may wish to configure both; note that pdfminer is extremely chatty at the
+    log level ``logging.INFO``.
+
+    This function does not set up the ``debug.log`` log file that the command
+    line interface does at certain verbosity levels. Applications should configure
+    their own debug logging.
 
     Args:
         verbosity (Verbosity): Verbosity level.
@@ -294,6 +307,9 @@ def ocr(  # pylint: disable=unused-argument
     }
     create_options_kwargs.update(kwargs)
 
+    if 'verbose' in kwargs:
+        warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
+
     options = create_options(**create_options_kwargs)
     check_options(options, _plugin_manager)
     return run_pipeline(options=options, plugin_manager=_plugin_manager, api=True)