Merge pull request #109 from cokelaer/main

add levenshtein function

README.rst

@@ -110,7 +110,7 @@ The **sequana_pipetools** package provide a standalone called **sequana_pipetool
 
 .. figure:: https://raw.githubusercontent.com/sequana/sequana_pipetools/main/doc/UI.png
 
-There are currently 3-4 main application. The first one is for Linux users under
+There are several applications. The first one is for Linux users under
 bash to obtain completion of a sequana pipeline command line arguments::
 
     sequana_pipetools --completion fastqc
@@ -126,7 +126,7 @@ This is used within th pipeline but can be used manually as well and is useful t
 The following command provides statistics about Sequana pipelines installed on your system (number of rules, wrappers
 used)::
 
-    sequana_pipetools -- stats
+    sequana_pipetools --stats
 
 And for developpers, a quick creation of schema file given a config file (experimental, developers would still need to edit the schema but it does 90% of the job)::
 
@@ -283,15 +283,14 @@ so, you will need to create an environment variable::
 
     export SEQUANA_WRAPPERS="git+file:///home/user/github/sequana-wrappers"
 
-If you decide to use singularity/apptainer, one common error on a cluster is that non-standard paths are not found. You can bind them using the -B option but a more general set up is to create thos environment variable::
+If you decide to use singularity/apptainer, one common error on a cluster is that non-standard paths are not found. You can bind them using the -B option but a more general set up is to create this environment variable::
 
     export SINGULARITY_BINDPATH="/path_to_bind"
 
-for Singularity setup, or ::
+for Apptainer setup ::
 
     export APPTAINER_BINDPATH="/path_to_bind"
 
-for Apptainer setup.
 
 
 What is Sequana ?
@@ -318,6 +317,7 @@ Changelog
 ========= ======================================================================
 Version   Description
 ========= ======================================================================
+1.0.3     * add levenshtein function. some typo corrections.
 1.0.2     * add the dot2png command. pin docutils <0.21 due to pip error
 1.0.1     * hot fix in the profile creation (regression)
 1.0.0     * Stable release

doc/conf.py

@@ -157,11 +157,11 @@
 # html_title = None
 
 # A shorter title for the navigation bar.  Default is the same as html_title.
-html_short_title = "sequana"
+html_short_title = "sequana_pipetools"
 
 # The name of an image file (relative to this directory) to place at the top
 # of the sidebar.
-# html_logo = "../../share/data/images/crx_logo.png"
+html_logo = "_static/logo_256x256.png"
 
 # The name of an image file (within the static path) to use as favicon of the
 # docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "poetry.core.masonry.api"
 #maintainer ?#maintainer email
 [tool.poetry]
 name = "sequana_pipetools"
-version = "1.0.2"
+version = "1.0.3"
 description = "A set of tools to help building or using Sequana pipelines"
 authors = ["Sequana Team"]
 license = "BSD-3"

sequana_pipetools/__init__.py

@@ -13,14 +13,14 @@ def get_package_version(package_name):
 
 from easydev.logging_tools import Logging
 
-logger = Logging("sequana_pipetools", "WARNING")
+logger = Logging("sequana_pipetools", "WARNING", "cyan")
 # To keep the inheritance/propagation of levels. Logging from easydev will do
 # the formatting only.
 import colorlog
 
 logger = colorlog.getLogger(logger.name)
 
-from .misc import url2hash
+from .misc import url2hash, levenshtein_distance
 from .sequana_manager import SequanaManager  # , get_pipeline_location
 from .snaketools import (
     Pipeline,

sequana_pipetools/info.py

@@ -18,11 +18,13 @@
 
 
 sequana_epilog = Colors().purple(
-    """If you use or like the Sequana project,
+"""\U00002139\U0000FE0F  To use completion, type 'sequana_pipetools --completion NAME'
+
+\u2705 If you use or like the Sequana project,
 please consider citing us (visit sequana.readthedocs.io for details) or use this
 citation:
 
-Cokelaer et al, (2017), ‘Sequana’: a Set of Snakemake NGS pipelines, Journal of
+\U0001F4DA Cokelaer et al, (2017), ‘Sequana’: a Set of Snakemake NGS pipelines, Journal of
 Open Source Software, 2(16), 352, JOSS DOI doi:10.21105/joss.00352
 
 

sequana_pipetools/misc.py

@@ -15,9 +15,58 @@
 
 from sequana_pipetools import get_package_version
 
-__all__ = ["Colors", "print_version", "error", "url2hash"]
+__all__ = ["Colors", "print_version", "error", "url2hash", "levenshtein_distance"]
 
 
+def levenshtein_distance(token1: str, token2: str) -> int:
+    """Computes the Levenshtein distance between two strings using dynamic programming.
+
+    The Levenshtein distance is a measure of the minimum number of single-character edits
+    (insertions, deletions, or substitutions) required to change one word into the other.
+
+    :param str token1: The first input string.
+    :param str token2: The second input string.
+    :return: Levenshtein distance between the two input strings.
+
+    Example::
+
+        >>> levenshtein_distance("kitten", "sitting")
+        3
+        >>> levenshtein_distance("flaw", "lawn")
+        2
+
+    Notes:
+    - The function uses a 2D list to store the distances, which requires O(m * n) space,
+      where m and n are the lengths of the input strings.
+    - The time complexity is O(m * n) since each cell of the matrix is filled once.
+
+    """
+    len1, len2 = len(token1), len(token2)
+
+    # Initialize the matrix with zeros
+    distances = [[0 for _ in range(len2 + 1)] for _ in range(len1 + 1)]
+
+    # Fill the first row and column
+    for t1 in range(len1 + 1):
+        distances[t1][0] = t1
+
+    for t2 in range(len2 + 1):
+        distances[0][t2] = t2
+
+    # Compute the Levenshtein distance
+    for t1 in range(1, len1 + 1):
+        for t2 in range(1, len2 + 1):
+            if token1[t1 - 1] == token2[t2 - 1]:
+                distances[t1][t2] = distances[t1 - 1][t2 - 1]
+            else:
+                distances[t1][t2] = min(
+                    distances[t1][t2 - 1],  # Insertion
+                    distances[t1 - 1][t2],  # Deletion
+                    distances[t1 - 1][t2 - 1]  # Substitution
+                ) + 1
+
+    return distances[len1][len2]
+
 def url2hash(url):
     md5hash = hashlib.md5()
     md5hash.update(url.encode())

sequana_pipetools/options.py

@@ -198,7 +198,7 @@ def from_project_callback(ctx, param, value):
         if not value:
             return
         else:
-            # When --from-project is called, all value of arguments are are replaced by the ones
+            # When --from-project is called, all value of arguments are replaced by the ones
             # found in the config file. Therefore, users may ommit all arguments. However, some
             # may be compulsary, so we need to reset all 'required' arguments to False
             for option in ctx.command.params:

sequana_pipetools/scripts/main.py

@@ -227,15 +227,16 @@ def main(**kwargs):
             subprocess.call(cmd.split())
 
     elif kwargs["completion"]:
+        name = kwargs["completion"]
+
         if kwargs["force"] is True:
             choice = "y"
         else:  # pragma: no cover
-            msg = "This action will replace files stored in ./config/sequana/pipelines. Do you want to proceed y/n: "
+            msg = f"This action will replace the {name}.sh file stored in ~/.config/sequana/pipelines. Do you want to proceed y/n: "
             choice = input(msg)
         if choice != "y":  # pragma: no cover
             sys.exit(0)
 
-        name = kwargs["completion"]
         try:
             c = ClickComplete(name)
             c.save_completion_script()
@@ -244,7 +245,7 @@ def main(**kwargs):
         finally:
             click.echo("Please source the files using:: \n")
             click.echo("    source ~/.config/sequana/pipelines/{}.sh".format(name))
-            click.echo("\nto activate the completion")
+            click.echo("\nto activate the completion. Add the line above in your environement")
     elif kwargs["stats"]:
         wrappers, rules = get_pipeline_statistics()
         click.echo("\n ==== Number of wrappers per pipeline")

sequana_pipetools/snaketools/pipeline_manager.py

@@ -172,6 +172,7 @@ def teardown(self, extra_dirs_to_remove=[], extra_files_to_remove=[], outdir="."
             print("\u2705 Another successful analysis. Open summary.html in your browser. Have fun.")
         else:
             print("\u2705 Another successful analysis. Have fun.")
+        print("\u2705 Please consider citing us would you use Sequana in your research. See https://sequana.readthedocs.io or cite: \n\n\tCokelaer et al. Sequana': a Set of Snakemake NGS pipelines, (2007) JOSS 2(16)")
 
     def get_html_summary(self, float="left", width=30):
         import pandas as pd

sequana_pipetools/snaketools/profile.py

@@ -17,7 +17,7 @@ def create_profile(workdir: Path, profile: str, **kwargs) -> str:
         with open(profile_file, "r") as fin:
             profile_text = fin.read()
             profile_text = profile_text.format(**kwargs)
-    except AttributeError:
+    except AttributeError: #pragma: no cover
         # python 3.8 support for back compatibility
         with resources.path("sequana_pipetools.resources", f"{profile}.yaml") as profile_file:
             profile_text = profile_file.read_text().format(**kwargs)

sequana_pipetools/snaketools/sequana_config.py

@@ -185,7 +185,7 @@ def check_config_with_schema(self, schemafile):
         try:
             ext_name = resources.files("sequana_pipetools.resources").joinpath("ext.py")
             extensions = [str(ext_name)]
-        except AttributeError:
+        except AttributeError: #pragma: no cover
             with resources.path("sequana_pipetools.resources", "ext.py") as ext_name:
                 extensions = [str(ext_name)]
 

tests/test_misc.py

@@ -1,4 +1,10 @@
-from sequana_pipetools.misc import Colors, print_version, error, url2hash
+from sequana_pipetools.misc import Colors, print_version, error, url2hash, levenshtein_distance
+
+
+
+def test_levenshtein():
+    assert levenshtein_distance("kitten", "sitting") == 3
+    assert levenshtein_distance("flaw", "lawn") == 2
 
 
 def test_url2hash():