cleaning, fixed indentation, styling

spip2md/__init__.py

@@ -3,12 +3,10 @@
 import sys
 from os import makedirs
 from shutil import rmtree
-from typing import Any
-
-from peewee import ModelSelect
 
 from spip2md.config import CFG
 from spip2md.database import DB
+from spip2md.regexmap import SPECIAL_OUTPUT
 from spip2md.spipobjects import RootRubrique, Rubrique
 
 # Define styles
@@ -25,66 +23,25 @@ C1 = 96  # Color
 C2 = 96  # Color
 
 
-# Print a stylized string, without trailing newline
+# Terminal escape sequence
-def style(string: str, *args: int, end: str = "") -> None:
+def esc(*args: int) -> str:
-    esc = "\033["  # Terminal escape sequence, needs to be closed by "m"
     if len(args) == 0:
-        params: str = "1;"  # Defaults to bold
+        params: str = "0;"  # Defaults to reset
     else:
         params: str = ""
+    # Build a string from args, that will be stripped from its trailing ;
     for a in args:
         params += str(a) + ";"
-    print(esc + params[:-1] + "m" + string + esc + "0m", end=end)
+    # Base terminal escape sequence that needs to be closed by "m"
-
+    return "\033[" + params[:-1] + "m"
-
-# Print a string, highlighting every substring starting at start_stop[x][0] …
-def highlight(string: str, *start_stop: tuple[int, int], end: str = "") -> None:
-    previous_stop = 0
-    for start, stop in start_stop:
-        print(string[previous_stop:start], end="")
-        style(string[start:stop], BOLD, RED)
-        previous_stop = stop
-    print(string[previous_stop:], end=end)
-
-
-# Query the DB to retrieve all sections without parent, sorted by publication date
-def root_sections(limit: int = 10**3) -> ModelSelect:
-    return (
-        Rubrique.select()
-        .where(Rubrique.id_parent == 0)
-        .order_by(Rubrique.date.desc())
-        .limit(limit)
-    )
-
-
-r"""
-# Print the detected unknown chars in article in their context but highlighted
-def warn_unknown_chars(article: Article) -> None:
-    # Print the title of the article in which there is unknown characters
-    # & the number of them
-    unknown_chars_apparitions: list[str] = unknown_chars_context(article.texte)
-    nb: int = len(unknown_chars_apparitions)
-    s: str = "s" if nb > 1 else ""
-    style(f"{nb}")
-    print(f" unknown character{s} in", end="")
-    style(f" {article.lang} ")
-    highlight(article.titre, *unknown_chars(article.titre))
-    print()  # Break line
-    # Print the context in which the unknown characters are found
-    for text in unknown_chars_apparitions:
-        style("  … ")
-        highlight(text, *unknown_chars(text))
-        style(" … \n")
-    print()  # Break line
-"""
 
 
 # Print one root section list output correctly
 # sys.setrecursionlimit(2000)
 def print_output(
-    tree: list[Any],
+    tree: list[str | list[str | list]],
     indent: str = "  ",
-    depth: int = 0,
+    depth: int = -1,
     branches: int = 1,
     leaves: int = 0,
 ) -> tuple[int, int]:
@@ -93,8 +50,11 @@ def print_output(
             branches, leaves = print_output(
                 sub, indent, depth + 1, branches + 1, leaves
             )
-        else:
+        elif type(sub) == str:
             leaves += 1
+            # Highlight special elements (in red for the moment)
+            for elmnt in SPECIAL_OUTPUT:
+                sub = elmnt.sub(esc(BOLD, GREEN) + r"\1" + esc(), sub)
             print(indent * depth + sub)
     return (branches, leaves)
 
@@ -125,12 +85,58 @@ def main(*argv):
     root: Rubrique = RootRubrique()
 
     # Write everything & print the output human-readably
-    sections, articles = print_output(root.write_tree(CFG.output_dir))
+    branches, leaves = print_output(root.write_tree(CFG.output_dir))
     # End, summary message
-    print(f"Exported a total of {sections} sections, containing {articles} articles")
+    print(
+        f"""
+Exported a total of {leaves} Markdown files, stored into {branches} directories"""
+    )
 
     # print()  # Break line between export & unknown characters warning
     # Warn about each article that contains unknown(s) character(s)
     # TODO do it with Python warnings
 
     DB.close()  # Close the connection with the database
+
+
+r""" OLD CODE
+# Print the detected unknown chars in article in their context but highlighted
+def warn_unknown_chars(article: Article) -> None:
+    # Print the title of the article in which there is unknown characters
+    # & the number of them
+    unknown_chars_apparitions: list[str] = unknown_chars_context(article.texte)
+    nb: int = len(unknown_chars_apparitions)
+    s: str = "s" if nb > 1 else ""
+    style(f"{nb}")
+    print(f" unknown character{s} in", end="")
+    style(f" {article.lang} ")
+    highlight(article.titre, *unknown_chars(article.titre))
+    print()  # Break line
+    # Print the context in which the unknown characters are found
+    for text in unknown_chars_apparitions:
+        style("  … ")
+        highlight(text, *unknown_chars(text))
+        style(" … \n")
+    print()  # Break line
+
+# Return a list of tuples giving the start and end of unknown substring in text
+def unknown_chars(text: str) -> list[tuple[int, int]]:
+    positions: list[tuple[int, int]] = []
+    for char in UNKNOWN_ISO:
+        for match in finditer("(" + char + ")+", text):
+            positions.append((match.start(), match.end()))
+    return positions
+
+# Return strings with unknown chards found in text, surrounded by context_length chars
+def unknown_chars_context(text: str, context_length: int = 24) -> list[str]:
+    errors: list[str] = []
+    context: str = r".{0," + str(context_length) + r"}"
+    for char in UNKNOWN_ISO:
+        matches = finditer(
+            context + r"(?=" + char + r")" + char + context,
+            text,
+        )
+        for match in matches:
+            errors.append(match.group())
+    return errors
+"""

spip2md/regexmap.py

@@ -256,31 +256,7 @@ UNKNOWN_ISO = (
 
 # Special elements in terminal output to surround
 SPECIAL_OUTPUT = (
-    (compile(r"^([0-9]+?\.)(?= )"), r"{}\1{}"),  # Counter
+    compile(r"^([0-9]+?\.)(?= )"),  # Counter
-    (compile(r"(?<= )->(?= )"), r"{}->{}"),  # Arrow
+    compile(r"(?<= )(->)(?= )"),  # Arrow
-    (compile(r"(?<=^Exporting )([0-9]+?)(?= )"), r"{}\1{}"),  # Total
+    compile(r"(?<=^Exporting )([0-9]+?)(?= )"),  # Total
 )
-
-
-r"""
-# Return a list of tuples giving the start and end of unknown substring in text
-def unknown_chars(text: str) -> list[tuple[int, int]]:
-    positions: list[tuple[int, int]] = []
-    for char in UNKNOWN_ISO:
-        for match in finditer("(" + char + ")+", text):
-            positions.append((match.start(), match.end()))
-    return positions
-
-# Return strings with unknown chards found in text, surrounded by context_length chars
-def unknown_chars_context(text: str, context_length: int = 24) -> list[str]:
-    errors: list[str] = []
-    context: str = r".{0," + str(context_length) + r"}"
-    for char in UNKNOWN_ISO:
-        matches = finditer(
-            context + r"(?=" + char + r")" + char + context,
-            text,
-        )
-        for match in matches:
-            errors.append(match.group())
-    return errors
-"""

spip2md/spipobjects.py

@@ -406,6 +406,7 @@ class RootRubrique(Rubrique):
         # 0 ID
         self.id_rubrique = 0
         # self.object_id = 0
+        self.profondeur = 0
 
     def write_tree(
         self, parent_dir: str, sections_limit: int = 0, articles_limit: int = 0
@@ -414,9 +415,11 @@ class RootRubrique(Rubrique):
         output: list[str | list[Any]] = []
         # Starting message
         output.append(
-            f"Begin converting {CFG.db}@{CFG.db_host} db to plain Markdown+YAML files"
+            f"""\
+Begin exporting `{CFG.db}@{CFG.db_host}` SPIP database to plain Markdown+YAML
+files into the directory `{parent_dir}`, as database user `{CFG.db_user}`
+"""
         )
-        output.append(f" as db user {CFG.db_user}, into the directory {parent_dir}")
         # Get all child section of self
         child_sections = (
             Rubrique.select()