From c147ad8db79793a62613e6bdbfc3ca5f384eb0e3 Mon Sep 17 00:00:00 2001
From: Roy Eric <139973278+Randomidous@users.noreply.github.com>
Date: Wed, 23 Apr 2025 11:38:31 +0200
Subject: [PATCH 1/3] add function to concatenate HTML files, such as reports
---
doc/changes/devel/13223.newfeature.rst | 1 +
mne/report/report.py | 88 ++++++++++++++++++++++++++
mne/report/tests/test_report.py | 45 +++++++++++++
pyproject.toml | 1 +
4 files changed, 135 insertions(+)
create mode 100644 doc/changes/devel/13223.newfeature.rst
diff --git a/doc/changes/devel/13223.newfeature.rst b/doc/changes/devel/13223.newfeature.rst
new file mode 100644
index 00000000000..88f34b27cdc
--- /dev/null
+++ b/doc/changes/devel/13223.newfeature.rst
@@ -0,0 +1 @@
+Add functionality to concatenate HTML files, such as mne.Reports, by `Roy Eric Wieske`_.
diff --git a/mne/report/report.py b/mne/report/report.py
index be7c716cdc0..477ca8dffec 100644
--- a/mne/report/report.py
+++ b/mne/report/report.py
@@ -23,6 +23,7 @@
from shutil import copyfile
import numpy as np
+from bs4 import BeautifulSoup, Comment, Tag
from .. import __version__ as MNE_VERSION
from .._fiff.meas_info import Info, read_info
@@ -675,6 +676,93 @@ def open_report(fname, **params):
return report
+def concatenate_reports(html_files, output_file):
+ """Concatenate multiple HTML files into one.
+
+ This function reads multiple HTML files, extracts their and sections,
+ and combines them into a single HTML file. It also handles duplicate IDs in the body
+ by removing them.
+
+ Parameters
+ ----------
+ html_files : list of str or Path
+ List of paths to the HTML files to be concatenated.
+ output_file : str or Path
+ Path to the output HTML file.
+
+ Returns
+ -------
+ final_html : BeautifulSoup
+ A BeautifulSoup object representing the combined HTML content.
+ """
+ combined_head = BeautifulSoup("", "lxml").head
+ combined_body = BeautifulSoup("", "lxml").body
+ used_ids = set()
+
+ for file in html_files:
+ file = Path(file)
+ with open(file, encoding="utf-8") as f:
+ soup = BeautifulSoup(f, "lxml")
+
+ toc = soup.find(id="toc") or soup.find(class_="toc")
+ if toc:
+ toc.decompose()
+
+ # handle head
+ if soup.head:
+ seen_styles = set()
+ seen_links = set()
+ seen_scripts = set()
+
+ for tag in soup.head.find_all(["script", "link", "style"], recursive=True):
+ tag_str = str(tag)
+ if tag.name == "style":
+ if tag_str in seen_styles:
+ continue
+ seen_styles.add(tag_str)
+ elif tag.name == "link":
+ if tag_str in seen_links:
+ continue
+ seen_links.add(tag_str)
+ elif tag.name == "script":
+ if tag_str in seen_scripts:
+ continue
+ seen_scripts.add(tag_str)
+
+ combined_head.append(tag)
+
+ # handle body
+ if soup.body:
+ section = soup.new_tag("section")
+ section.append(soup.new_tag("hr"))
+ section.append(Comment(f"START {file.name}"))
+
+ for tag in soup.body.contents:
+ if isinstance(tag, Tag):
+ for t in tag.find_all(True):
+ id_ = t.get("id")
+ if id_:
+ if id_ in used_ids:
+ del t["id"]
+ else:
+ used_ids.add(id_)
+
+ section.append(tag)
+
+ combined_body.append(section)
+
+ # create final HTML
+ final_html = BeautifulSoup("", "lxml")
+ final_html.html.append(combined_head)
+ final_html.html.append(combined_body)
+
+ output_file = Path(output_file)
+ with output_file.open("w", encoding="utf-8") as f:
+ f.write(final_html.prettify())
+
+ return final_html
+
+
###############################################################################
# HTML scan renderer
diff --git a/mne/report/tests/test_report.py b/mne/report/tests/test_report.py
index 66f4cd9e336..fb33c2ff891 100644
--- a/mne/report/tests/test_report.py
+++ b/mne/report/tests/test_report.py
@@ -13,6 +13,7 @@
import numpy as np
import pytest
+from bs4 import BeautifulSoup
from matplotlib import pyplot as plt
from mne import (
@@ -33,6 +34,7 @@
from mne.report.report import (
_ALLOWED_IMAGE_FORMATS,
CONTENT_ORDER,
+ concatenate_reports,
)
from mne.utils import Bunch, _record_warnings
from mne.utils._testing import assert_object_equal
@@ -634,6 +636,49 @@ def test_open_report(tmp_path):
assert h5io.read_hdf5(hdf5, title="companion") == "test"
+def test_concatenate_reports(tmp_path, sample_meg_dir):
+ """Test the concatenate_reports function."""
+ raw_path = sample_meg_dir / "sample_audvis_raw.fif"
+ raw = read_raw_fif(raw_path, preload=True)
+ raw.set_annotations(None)
+ raw.crop(0, 20)
+
+ with tmp_path as tmp_dir:
+ tmp_path = Path(tmp_dir)
+
+ # Report 1 with custom content
+ report1 = Report(title="Report eeg_preprocessing #1")
+ report1.add_html(
+ "This is report one
", title="Note 1"
+ )
+ report1.add_raw(raw, title="Raw data", psd=False)
+ report1.save(tmp_path / "report1.html", overwrite=True, open_browser=False)
+
+ # Report 2 with different custom content
+ report2 = Report(title="Report eeg_preprocessing #2")
+ report2.add_html(
+ "This is report two
", title="Note 2"
+ )
+ report2.add_raw(raw, title="Raw data", psd=False)
+ report2.save(tmp_path / "report2.html", overwrite=True, open_browser=False)
+
+ file1 = tmp_path / "report1.html"
+ file2 = tmp_path / "report2.html"
+ output_file = tmp_path / "combined.html"
+
+ _ = concatenate_reports([file1, file2], output_file)
+
+ assert output_file.exists()
+
+ with open(output_file, encoding="utf-8") as f:
+ out_html = BeautifulSoup(f, "lxml")
+
+ assert out_html.head is not None
+ assert out_html.body is not None
+ assert out_html.find(text=lambda t: "This is report one" in t) is not None
+ assert out_html.find(text=lambda t: "This is report two" in t) is not None
+
+
def test_remove():
"""Test removing figures from a report."""
r = Report()
diff --git a/pyproject.toml b/pyproject.toml
index 59e5a1703e3..60b95f257d6 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -88,6 +88,7 @@ full = ["mne[full-no-qt]", "PyQt6 != 6.6.0", "PyQt6-Qt6 != 6.6.0, != 6.7.0"]
# and mne[full-pyside6], which will install PySide6 instead of PyQt6.
full-no-qt = [
"antio >= 0.5.0",
+ "beautifulsoup4",
"darkdetect",
"defusedxml",
"dipy",
From d54b34d4b120f07a4be198453ddd2feea26e9f98 Mon Sep 17 00:00:00 2001
From: Roy Eric <139973278+Randomidous@users.noreply.github.com>
Date: Wed, 23 Apr 2025 14:20:39 +0200
Subject: [PATCH 2/3] update doc/changes/devel
---
doc/changes/devel/13223.newfeature.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/doc/changes/devel/13223.newfeature.rst b/doc/changes/devel/13223.newfeature.rst
index 88f34b27cdc..88f45bf44aa 100644
--- a/doc/changes/devel/13223.newfeature.rst
+++ b/doc/changes/devel/13223.newfeature.rst
@@ -1 +1 @@
-Add functionality to concatenate HTML files, such as mne.Reports, by `Roy Eric Wieske`_.
+Add functionality to :func:`mne.report.concatenate_reports` concatenate HTML files, such as mne.Reports, by `Roy Eric Wieske`_.
From f57c373af961b1e620ba86de5e2a403a8d574629 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
<66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 23 Apr 2025 12:21:29 +0000
Subject: [PATCH 3/3] [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---
environment.yml | 1 +
1 file changed, 1 insertion(+)
diff --git a/environment.yml b/environment.yml
index 78c773e56bf..76c3187ab8e 100644
--- a/environment.yml
+++ b/environment.yml
@@ -5,6 +5,7 @@ channels:
dependencies:
- python >=3.10
- antio >=0.5.0
+ - beautifulsoup4
- darkdetect
- decorator
- defusedxml