Skip to content

Make links working, improve security #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
chrootlogin wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Make links working, improve security #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8debb32
fix: url handling for links
chrootlogin Mar 22, 2025
faf8726
fix: improve path building by setting source route as /
chrootlogin Mar 22, 2025
11e3fec
fix: use correct pattern for app_ver in setup.py
chrootlogin Mar 22, 2025
802d418
fix: use correct dir pattern
chrootlogin Mar 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
123 changes: 70 additions & 53 deletions linuxdir2html/linuxdir2html.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,23 +25,22 @@
import re

# Most of the following variables are to replace placeholders in template.html
appName = "LinuxDir2HTML"
app_ver = "1.6.1"
gen_date = datetime.datetime.now().strftime("%m/%d/%Y")
gen_time = datetime.datetime.now().strftime("%H:%M")
app_link = "https://github.com/homeisfar/LinuxDir2HTML"
dir_data = ""
total_numFiles = 0
total_numDirs = 0
grand_total_size= 0
file_links = "false" # This is a string b/c it's used in the html template.
link_protocol = "file://"
include_hidden = False
follow_symlink = False
dir_results = []
childList_names = [] # names supplied from --child options
startsList_names = [] # dir's generated from --startsfrom options
# linkRoot = "/" # [LINK ROOT] is fixed as '' (see generateHTML)
appName = "LinuxDir2HTML"
app_ver = "1.6.1"
gen_date = datetime.datetime.now().strftime("%m/%d/%Y")
gen_time = datetime.datetime.now().strftime("%H:%M")
app_link = "https://github.com/homeisfar/LinuxDir2HTML"
dir_data = ""
total_numFiles = 0
total_numDirs = 0
grand_total_size = 0
file_links = "false" # This is a string b/c it's used in the html template.
link_protocol = ""
include_hidden = False
follow_symlink = False
dir_results = []
childList_names = [] # names supplied from --child options
startsList_names = [] # dir's generated from --startsfrom options

parser = argparse.ArgumentParser(description='Generate HTML view of the file system.\n')
parser.add_argument('pathToIndex', help='Path of Directory to Index')
Expand All @@ -50,15 +49,17 @@
parser.add_argument('--startswith', action='append', help='[DEPRECATED] Start of name(s) of children dirs to include')
parser.add_argument('--hidden', help='Include hidden files (leading with .)', action="store_true")
parser.add_argument('--links', help='Create links to files in HTML output', action="store_true")
parser.add_argument('--protocol', help='Protocol used for links (used with --links)', default="http://")
parser.add_argument('--symlink', help='Follow symlinks. WARN: This can cause infinite loops.', action="store_true")
parser.add_argument('-v', '--verbose', help='increase output verbosity. -v or -vv for more.', action="count")
parser.add_argument('--silent', help='Suppress terminal output except on error.', action="store_true")
parser.add_argument('--version', help='Print version and exit', action="version", version=app_ver)


def main():
global include_hidden, file_links, childList_names, startsList_names, follow_symlink
global include_hidden, file_links, childList_names, startsList_names, follow_symlink, link_protocol
args = parser.parse_args()

## Initialize logging facilities
log_level = logging.WARNING
if args.verbose:
Expand All @@ -70,13 +71,16 @@ def main():
log_level = logging.ERROR
logging.basicConfig(format='%(asctime)s %(message)s', datefmt='%H:%M:%S', level=log_level)
log_name = logging.getLevelName(logging.getLogger().getEffectiveLevel())
logging.info( f'Logging Level {log_name}')
logging.info(f'Logging Level {log_name}')

# Handle user input flags and options
pathToIndex = args.pathToIndex
title = args.outputfile
if args.links:
file_links = "true"
link_protocol = args.protocol
logging.info(f"Using protocol for links: {link_protocol}")

if args.hidden:
include_hidden = True
if args.symlink:
Expand All @@ -88,11 +92,10 @@ def main():
if os.path.isdir(title):
logging.error(f"Chosen output file [{title}] is a directory. Aborting.")
exit(1)

logging.info(f"Creating file links is [{file_links}]")
logging.info(f"Showing hidden items is [{include_hidden}]")
logging.info(f"Following symlinks is [{follow_symlink}]")

# check that no child or startswith arg include a path separator
for child_val in args.child or []:
if os.sep in child_val:
Expand All @@ -104,7 +107,6 @@ def main():
logging.error(f"startswith argument [{start_val}] contains a path separator.")
exit(1)
startsList_names.append(os.path.normcase(start_val))

# Time to do the real work. Generate array with our file & dir entries,
# then generate the resulting HTML
pathToIndex = Path(pathToIndex).resolve()
Expand All @@ -114,70 +116,83 @@ def main():
generateHTML(
dir_data, appName, app_ver, gen_date, gen_time, title, app_link,
total_numFiles, total_numDirs, grand_total_size, file_links
)
)
return

def generateDirArray(root_dir): # root i.e. user-provided root path, not "/"


def generateDirArray(root_dir): # root i.e. user-provided root path, not "/"
global dir_data, total_numFiles, total_numDirs, grand_total_size, \
dir_results, childList_names, startsList_names
dir_results, childList_names, startsList_names
id = 0
dirs_dictionary = {}


# Convert root_dir to string for path operations
root_str = str(root_dir)
# Ensure root_str does end with a separator to properly build path
if not root_str.endswith(os.sep):
root_str += os.sep

# We enumerate every unique directory, ignoring symlinks by default.
first_iteration = True
for current_dir, dirs, files in os.walk(root_dir, True, None, follow_symlink):
logging.debug( f'Walking Dir [{current_dir}]')
logging.debug(f'Walking Dir [{current_dir}]')

# If --child or --startswith are used, only add the requested
# directories. This will only be performed on the root_dir
if first_iteration:
first_iteration = False
if childList_names or startsList_names:
selectDirs(current_dir, dirs, include_hidden)
files = []

if include_hidden is False:
dirs[:] = [d for d in dirs if not d[0] == '.']
files = [f for f in files if not f[0] == '.']

dirs = sorted(dirs, key=str.casefold)
files = sorted(files, key=str.casefold)

# Create a relative path by removing root_dir from current_dir
rel_dir = str(current_dir)
if rel_dir.startswith(root_str):
rel_dir = rel_dir[len(root_str):]
elif rel_dir == root_str[:-1]: # If it's the root directory itself
rel_dir = "/"

if not rel_dir.startswith("/"):
rel_dir = "/" + rel_dir

# The key is the current dir, and the value is described as follows.
# A four index array like so:
# | 0 | 1 | 2 | 3 |
# | id | file_attrs | dir total file size | sub dirs |
# [1] is an array with the current directory path and modification time, then
# [1] is an array with the current directory path and modification time, then
# is followed by the directory's files. Each file has a size and modtime.
# Id is unused but could be useful for future features.
dirs_dictionary[current_dir] = [id, [], 0, '']
arr = dirs_dictionary[current_dir][1]
dir_mod_time = int(
datetime.datetime.fromtimestamp(
os.path.getmtime(current_dir)).timestamp())
arr.append(f'{json.dumps(current_dir)[1:-1]}\0000\0{dir_mod_time}')

datetime.datetime.fromtimestamp(
os.path.getmtime(current_dir)).timestamp())
arr.append(f'{json.dumps(rel_dir)[1:-1]}\0000\0{dir_mod_time}')
##### Enumerate FILES #####
total_size = 0
for file in files:
full_file_path = os.path.join(current_dir, file)

if os.path.isfile(full_file_path):
total_numFiles += 1
file_size = os.path.getsize(full_file_path)
total_numFiles += 1
file_size = os.path.getsize(full_file_path)
if (os.path.islink(full_file_path)):
file_size = os.lstat(full_file_path).st_size
total_size += file_size
total_size += file_size
grand_total_size += file_size
try: # Avoid possible invalid mtimes
mod_time = int(datetime.datetime.fromtimestamp
(os.path.getmtime(full_file_path)).timestamp())
(os.path.getmtime(full_file_path)).timestamp())
except:
logging.warning(f'----fromtimestamp timestamp invalid [{full_file_path}]')
mod_time = 1
arr.append(f'{json.dumps(file)[1:-1]}\0{file_size}\0{mod_time}')
dirs_dictionary[current_dir][2] = total_size

##### Enumerate DIRS #####
dir_links = ''
for dir in dirs:
Expand All @@ -189,7 +204,6 @@ def generateDirArray(root_dir): # root i.e. user-provided root path, not "/"
dirs_dictionary[full_dir_path] = [id, [dir], 0, '']
dir_links += f'{id}\0'
dirs_dictionary[current_dir][3] = dir_links[:-1]

## Output format follows:
# "FILE_PATH\00\0MODIFIED_TIME","FILE_NAME\0FILE_SIZE\0MODIFIED_TIME",DIR_SIZE,"DIR1\0DIR2..."
# To get a practical sense of what this means, look at a generated output after using the program.
Expand All @@ -202,6 +216,7 @@ def generateDirArray(root_dir): # root i.e. user-provided root path, not "/"
dir_results.append(dir_data)
return


# This function will execute only on the first iteration of the directory walk.
# It only has an effect if --child or --startswith are used.
def selectDirs(current_dir, dirs, include_hidden):
Expand All @@ -211,11 +226,11 @@ def selectDirs(current_dir, dirs, include_hidden):
if startsList_names:
logging.warning(f'Using dirs starting with [{str(startsList_names)[1:-1]}]')
if include_hidden:
hidden_dirs = ["."+d for d in startsList_names]
hidden_dirs = ["." + d for d in startsList_names]
logging.warning(f'Hidden flag set. Using dirs starting with [{str(hidden_dirs)[1:-1]}]')

desired_dirs = startsList_names + hidden_dirs
for i in range(len(dirs) -1, -1, -1):
for i in range(len(dirs) - 1, -1, -1):
keep_dir = '?'
for desired in desired_dirs:
if re.match(desired, dirs[i], re.I) or dirs[i] in childList_names:
Expand All @@ -226,18 +241,19 @@ def selectDirs(current_dir, dirs, include_hidden):
logging.info(f'Dirs selected:\n{dirs}')
return


def generateHTML(
dir_data, appName, app_ver, gen_date, gen_time, title,
app_link, numFiles, numDirs, grand_total_size, file_links
):
dir_data, appName, app_ver, gen_date, gen_time, title,
app_link, numFiles, numDirs, grand_total_size, file_links
):
template_file = open((Path(__file__).parent / 'template.html'), 'r', encoding="utf-8")
output_file = open(f'{title}.html', 'w', encoding="utf-8", errors='xmlcharrefreplace')
for line in template_file:
modified_line = line
if '[DIR DATA]' in modified_line:
for line in dir_results:
try: # can error if encoding mismatch; can't fix, just report
# TODO: investigate if the above is true after v1.6.1
# TODO: investigate if the above is true after v1.6.1
output_file.write(f'{line}')
except:
logging.warning(f'----output_file.write error [{line}]')
Expand All @@ -261,5 +277,6 @@ def generateHTML(
logging.warning("Wrote output to: " + os.path.realpath(output_file.name))
return


if __name__ == '__main__':
main()
main()
7 changes: 6 additions & 1 deletion linuxdir2html/template.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1309,7 +1309,12 @@
let file_tmp = sTmp[0];
if( linkFiles )
{
const url = encodeURI(`${linkProtocol}${dir}/${filename}`);
let url;
if( dir === "/" ) {
url = encodeURI(`${linkProtocol}/${filename}`);
} else {
url = encodeURI(`${linkProtocol}${dir}/${filename}`);
}
file_tmp = `<a href=${url}>${filename}</a>`;
}

Expand Down
2 changes: 1 addition & 1 deletion setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
long_description = fh.read()

version = re.search(
r'(app_ver = "(\d.\d.\d)")',
r'(app_ver = "(\d.\d.\d)")',
open("linuxdir2html/linuxdir2html.py").read(),
re.M
).group(2)
Expand Down