From da028192c960d009c7c9a8b2064bc6e37f58f955 Mon Sep 17 00:00:00 2001
From: Holger Frey <frey@imtek.de>
Date: Wed, 19 Jan 2022 14:57:35 +0100
Subject: [PATCH] added excel2pylist

---
 README.md                    |  2 +-
 pyproject.toml               |  1 +
 work_helpers/excel2pylist.py | 59 ++++++++++++++++++++++++++++++++++++
 3 files changed, 61 insertions(+), 1 deletion(-)
 create mode 100644 work_helpers/excel2pylist.py

diff --git a/README.md b/README.md
index 39d83c7..af14ff0 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,7 @@ Some helper scripts for the day to day work with Ubuntu in WSL2
  - **sg_list_frms**: collect gitea issues and related frm filenames
  - **xls2changelog**: reformat copied excel data to the safeguard changelog format
  - **xls2markdown**: reformat copied excel data to a markdown table
-
+ - **xls2pylist**: reformat copied excel data to a python list
 
 
 Proposed workflow for Safeguard projects
diff --git a/pyproject.toml b/pyproject.toml
index 2760bb0..d03f488 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -22,6 +22,7 @@ requires = [
 [tool.flit.scripts]
 xls2changelog = "work_helpers.excel2changelog:cli"
 xls2markdown = "work_helpers.excel2markdown:cli"
+xls2pylist = "work_helpers.excel2pylist:cli"
 sg_mbp_release = "work_helpers.sg_mbp_release:sg_mbp_release"
 sg_mbp_new_version = "work_helpers.sg_mbp_release:sg_mbp_new_version"
 sg_list_frms = "work_helpers.sg_frm_list:cli"
diff --git a/work_helpers/excel2pylist.py b/work_helpers/excel2pylist.py
new file mode 100644
index 0000000..5feb6e9
--- /dev/null
+++ b/work_helpers/excel2pylist.py
@@ -0,0 +1,59 @@
+import click
+import pyperclip
+
+def _strip_parts(iterable):
+    return [item.strip() for item in iterable]
+
+def _remove_item_two(iterable):
+    """ remove the second item from parts, it's the probe name """
+    copied = iterable.copy()
+    copied.pop(1)  # zero based index
+    return copied
+
+def _replace_empty_strings(iterable, replacement="None"):
+    return [i or replacement for i in iterable]
+
+def prepare(text):
+    lines = text.splitlines()
+
+    # replacing the german decimal separator with the standard english dot
+    correct_separator = (l.replace(",", ".") for l in lines)
+    parted = (l.split("\t") for l in correct_separator)
+    stripped = (_strip_parts(l) for l in parted)
+    no_probe_name = (_remove_item_two(l) for l in stripped)
+    return [_replace_empty_strings(l) for l in no_probe_name]
+
+
+def get_cell_lengths(table):
+    # get the max lenght of each column
+    in_columns = zip(*table)
+    columns_lenghts = (map(len, c) for c in in_columns)
+    return [max(c) for c in columns_lenghts]
+
+
+def pad_field(index, t):
+    value, length = t
+    if index == 0:
+        return value.rjust(length)
+    else:
+        return value.ljust(length)
+
+def pad_fields(iterable, lengths):
+    return [pad_field(i, t) for i, t in enumerate(zip(iterable, lengths))]
+
+def build_list(table, lengths):
+    padded = (pad_fields(l) for l in lines)
+    padded_lines = (", ".join(l) for l in padded)
+    lines_as_list = (f"    [{l}],  # noqa: E201, E202, E501," for l in padded_lines)
+    list_content = "\n".join(lines_as_list)
+    return f"[\n{list_content}\n]\n"
+
+
+@click.command()
+def cli():
+    xls = pyperclip.paste()
+    table = split_table(xls)
+    lengths = get_cell_lengths(table)
+    result = build_list(table, lengths)
+    print("copied to clipboard")
+    pyperclip.copy(result)
\ No newline at end of file