Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
C
caosdb-advanced-user-tools
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Iterations
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
caosdb
Software
caosdb-advanced-user-tools
Commits
99bb9dac
Commit
99bb9dac
authored
5 years ago
by
Henrik tom Wörden
Browse files
Options
Downloads
Patches
Plain Diff
read md
parent
cbc6067f
No related branches found
Branches containing commit
No related tags found
Tags containing commit
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
src/caosadvancedtools/read_md_header.py
+195
-0
195 additions, 0 deletions
src/caosadvancedtools/read_md_header.py
with
195 additions
and
0 deletions
src/caosadvancedtools/read_md_header.py
0 → 100644
+
195
−
0
View file @
99bb9dac
#!/usr/bin/env python
# encoding: utf-8
#
# ** header v3.0
# This file is a part of the CaosDB Project.
#
# Copyright (C)
# A. Schlemmer, 01/2019
# D. Hornung 2019-02
# T. Fitschen 2019-02
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as
# published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
#
# ** end header
#
import
os
import
re
import
yaml
TEMPLATEHEADER
=
"""
---
title: {title}
location:
author:
participants:
date: {date}
keywords:
tags:
category:
...
"""
def
_clean_header
(
header
):
# Fill empty fields with empty string
for
k
,
v
in
header
.
items
():
if
v
==
"
null
"
:
header
[
k
]
=
""
if
v
is
None
:
header
[
k
]
=
""
for
k
,
v
in
header
.
items
():
# Plain string is put into list
if
type
(
v
)
==
str
:
header
[
k
]
=
[
v
]
return
header
class
NoValidHeader
(
Exception
):
def
__init__
(
self
,
filename
,
*
args
,
**
kwargs
):
msg
=
(
"
Header missing in {}
\n
Fix this with the modify subcommand
"
"
using -f option
"
.
format
(
filename
))
super
().
__init__
(
msg
,
*
args
,
**
kwargs
)
def
get_header
(
filename
,
add_header
=
True
):
"""
Open an md file identified by filename and read out the yaml
header.
filename can also be a folder. In this case folder/readme.md will be used for
getting the header.
If a header is found a tuple is returned: (first yaml header line index, last+1
yaml header line index, header)
Otherwise, if `add_header` is True, a header is added and the function is called
again.
The header is normalized in the following way:
- If the value to a key is a string, a list with that string as only element is
returned.
From https://pandoc.org/MANUAL.html:
A YAML metadata block is a valid YAML object, delimited by a line of three
hyphens (---) at the top and a line of three hyphens (---) or three dots (...)
at the bottom. A YAML metadata block may occur anywhere in the document, but if
it is not at the beginning, it must be preceded by a blank line.
"""
if
os
.
path
.
isdir
(
filename
):
filename
=
os
.
path
.
join
(
filename
,
"
readme.md
"
)
with
open
(
filename
)
as
f
:
textlines
=
f
.
readlines
()
state
=
0
found_0
=
-
1
found_1
=
-
1
found_2
=
-
1
for
i
,
line
in
enumerate
(
textlines
):
if
len
(
line
)
==
1
and
state
in
{
-
1
,
0
}:
found_0
=
i
state
=
0
continue
if
line
.
rstrip
()
==
"
---
"
and
state
==
0
:
found_1
=
i
+
1
state
=
1
continue
if
line
.
rstrip
()
==
"
...
"
and
state
==
1
:
found_2
=
i
state
=
2
break
# Else: reset state to -1, unless it is 1 (in this case, leave it
# untouched
if
state
==
1
:
pass
else
:
state
=
-
1
# If a header section was found:
if
state
==
2
:
headerlines
=
[]
for
l
in
textlines
[
found_1
:
found_2
]:
l
=
l
.
replace
(
"
\t
"
,
"
"
)
l
=
l
.
rstrip
()
headerlines
.
append
(
l
)
try
:
yaml_part
=
yaml
.
load
(
"
\n
"
.
join
(
headerlines
))
except
yaml
.
error
.
MarkedYAMLError
as
e
:
# print("Error in file {}:".format(filename))
# print(headerlines)
raise
NoValidHeader
(
filename
)
return
(
found_1
,
found_2
,
_clean_header
(
yaml_part
))
if
not
add_header
:
raise
NoValidHeader
(
filename
)
else
:
print
(
"
Adding header in: {fn}
"
.
format
(
fn
=
filename
))
_add_header
(
filename
)
return
get_header
(
filename
)
def
get_date_and_title_from_name
(
filename
):
dir_re
=
re
.
compile
(
'
(?P<title>.+)\.(?P<date>[0-9\-]+)
'
)
file_re
=
re
.
compile
(
'
(?P<title>.+)\.(?P<date>[0-9\-]+)\.md
'
)
if
os
.
path
.
basename
(
filename
).
lower
()
==
"
readme.md
"
:
for
part
in
os
.
path
.
abspath
(
filename
).
split
(
os
.
path
.
sep
):
m
=
dir_re
.
match
(
part
)
if
m
is
not
None
:
break
else
:
m
=
file_re
.
match
(
filename
)
if
m
is
not
None
:
return
m
.
group
(
"
date
"
),
m
.
group
(
"
title
"
)
else
:
return
""
,
""
def
_add_header
(
filename
):
"""
Add a header to an md file. Date and title are guessed from the filename.
"""
with
open
(
filename
)
as
f
:
textlines
=
f
.
readlines
()
date
,
title
=
get_date_and_title_from_name
(
filename
)
localheader
=
TEMPLATEHEADER
.
format
(
date
=
str
(
date
),
title
=
title
)
with
open
(
filename
,
"
w
"
)
as
f
:
f
.
write
(
localheader
)
f
.
writelines
(
textlines
)
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment