diff --git a/.gitea/workflows/tests.yaml b/.gitea/workflows/tests.yaml index f56a490..a3adf0a 100644 --- a/.gitea/workflows/tests.yaml +++ b/.gitea/workflows/tests.yaml @@ -9,8 +9,8 @@ jobs: - name: Check out repository code uses: actions/checkout@v3 - run: apt-get update && apt-get install -y python3-pip - - run: pip install -e . - - run: pip install pytest + - run: pip install --break-system-package -e . + - run: pip install --break-system-package pytest - run: pytest mypy: @@ -19,8 +19,8 @@ jobs: - name: Check out repository code uses: actions/checkout@v3 - run: apt-get update && apt-get install -y python3-pip - - run: pip install -e . - - run: pip install mypy + - run: pip install --break-system-package -e . + - run: pip install --break-system-package mypy - run: mypy org_rw --check-untyped-defs style-formatting: @@ -29,8 +29,8 @@ jobs: - name: Check out repository code uses: actions/checkout@v3 - run: apt-get update && apt-get install -y python3-pip - - run: pip install -e . - - run: pip install black + - run: pip install --break-system-package -e . + - run: pip install --break-system-package black - run: black --check . style-sorted-imports: @@ -39,8 +39,8 @@ jobs: - name: Check out repository code uses: actions/checkout@v3 - run: apt-get update && apt-get install -y python3-pip - - run: pip install -e . - - run: pip install isort + - run: pip install --break-system-package -e . + - run: pip install --break-system-package isort - run: isort --profile black --check . stability-extra-test: @@ -49,5 +49,5 @@ jobs: - name: Check out repository code uses: actions/checkout@v3 - run: apt-get update && apt-get install -y git-core python3-pip - - run: pip install -e . + - run: pip install --break-system-package -e . - run: bash extra-tests/check_all.sh diff --git a/README.org b/README.org index 95ec98a..6f03720 100644 --- a/README.org +++ b/README.org @@ -7,6 +7,12 @@ A python library to parse, modify and save Org-mode files. - Modify these data and write it back to disk. - Keep the original structure intact (indentation, spaces, format, ...). +** Principles +- Avoid any dependency outside of Python's standard library. +- Don't do anything outside of the scope of parsing/re-serializing Org-mode files. +- *Modification of the original text if there's no change is considered a bug (see [[id:7363ba38-1662-4d3c-9e83-0999824975b7][Known issues]]).* +- Data structures should be exposed as it's read on Emacs's org-mode or when in doubt as raw as possible. +- Data in the objects should be modificable as a way to update the document itself. *Consider this a Object-oriented design.* ** Safety mechanism As this library is still in early development. Running it over files might produce unexpected changes on them. For this reason it's heavily recommended to @@ -21,6 +27,9 @@ Also, see [[id:76e77f7f-c9e0-4c83-ad2f-39a5a8894a83][Known issues:Structure modi not properly stored and can trigger this safety mechanism on a false-positive. * Known issues +:PROPERTIES: +:ID: 7363ba38-1662-4d3c-9e83-0999824975b7 +:END: ** Structure modifications :PROPERTIES: :ID: 76e77f7f-c9e0-4c83-ad2f-39a5a8894a83 diff --git a/org_rw/dom.py b/org_rw/dom.py index f9ed40f..baf0092 100644 --- a/org_rw/dom.py +++ b/org_rw/dom.py @@ -24,6 +24,14 @@ class ResultsDrawerNode(DrawerNode): return "".format(len(self.children)) +class GenericDrawerNode(DrawerNode): + def __init__(self, drawer_name): + self.drawer_name = drawer_name + + def __repr__(self): + return "".format(self.drawer_name, len(self.children)) + + class PropertyNode: def __init__(self, key, value): self.key = key @@ -62,12 +70,18 @@ class TableSeparatorRow: def __init__(self, orig=None): self.orig = orig + def get_raw(self): + return get_raw_contents(self.orig) + class TableRow: def __init__(self, cells, orig=None): self.cells = cells self.orig = orig + def get_raw(self): + return get_raw_contents(self.orig) + class Text: def __init__(self, content): diff --git a/org_rw/org_rw.py b/org_rw/org_rw.py index 558e7a2..6baadd1 100644 --- a/org_rw/org_rw.py +++ b/org_rw/org_rw.py @@ -122,6 +122,7 @@ NON_FINISHED_GROUPS = ( dom.ListGroupNode, dom.ResultsDrawerNode, dom.PropertyDrawerNode, + dom.GenericDrawerNode, ) FREE_GROUPS = (dom.CodeBlock,) @@ -329,7 +330,7 @@ class Headline: closed: Optional[Time] = None, ): self.start_line = start_line - self._depth = depth + self.depth = depth self.orig = orig self.properties = properties self.keywords = keywords @@ -414,6 +415,7 @@ class Headline: if ( isinstance(line, DelimiterLine) and line.delimiter_type == DelimiterLineType.END_BLOCK + and line.type_data.subtype == current_node.header.type_data.subtype ): start = current_node.header.linenum @@ -636,6 +638,13 @@ class Headline: assert current_node is None current_node = dom.ResultsDrawerNode() + # TODO: Allow indentation of these blocks inside others + indentation_tree = [current_node] + tree.append(current_node) + elif content.strip().startswith(":") and content.strip().endswith(":"): + assert current_node is None + current_node = dom.GenericDrawerNode(content.strip().strip(":")) + # TODO: Allow indentation of these blocks inside others indentation_tree = [current_node] tree.append(current_node) @@ -762,16 +771,6 @@ class Headline: pass self._state = new_state - @property - def depth(self): - return self._depth - - @depth.setter - def depth(self, value): - self._depth = value - for child in self.children: - child.depth = value + 1 - @property def clock(self): times = [] @@ -874,9 +873,24 @@ class Headline: yield from get_links_from_content(item.content) def get_lines_between(self, start, end): - for line in self.contents: + # @TODO: Generalize for other line types too. + everything = ( + [] + # + self.keywords + + self.contents + # + self.list_items + # + self.table_rows + # + self.properties + # + self.structural + + self.delimiters + ) + + for line in everything: if start <= line.linenum < end: - yield "".join(line.get_raw()) + if "get_raw" in dir(line): + yield "".join(line.get_raw()) + else: + yield line.line def get_contents(self, format): if format == "raw": @@ -1076,38 +1090,6 @@ class Headline: self.children.append(headline) return headline - def refile( - self, destination: Union["Headline", OrgDoc], top: bool = False - ) -> Union["Headline", OrgDoc]: - """Refile this headline to a new destination. - - Args: - destination: The headline to which this headline will be moved - top: Whether to append to bottom or insert at top of destination's children - - Returns: - The destination headline - """ - # Remove from the parent - if self.parent: - if isinstance(self.parent, Headline): - self.parent.children.remove(self) - else: - self.parent.headlines.remove(self) - - # Add ourselves to the destination - if top: - destination.children.insert(0, self) - else: - destination.children.append(self) - - # Adjust the depth - self.depth = destination.depth + 1 - - # Adjust our parent - self.parent = destination - return destination - RawLine = collections.namedtuple("RawLine", ("linenum", "line")) Keyword = collections.namedtuple( @@ -2349,6 +2331,7 @@ class OrgDoc: list_items, structural, properties, + delimiters, environment=BASE_ENVIRONMENT, ): self.todo_keywords = [HeadlineState(name=kw) for kw in DEFAULT_TODO_KEYWORDS] @@ -2378,6 +2361,7 @@ class OrgDoc: self.list_items: List[ListItem] = list_items self.structural: List = structural self.properties: List = properties + self.delimiters: List = delimiters self._path = None self.headlines: List[Headline] = list( map(lambda hl: parse_headline(hl, self, self), headlines) @@ -2408,24 +2392,6 @@ class OrgDoc: def shallow_tags(self) -> list[str]: return self.tags - @property - def depth(self): - """ - Attribute to be compatible with the signature of the Headlines. - - Useful when doing operations across the headline hierarchy - """ - return 0 - - @property - def children(self): - """ - Attribute to be compatible with the signature of the Headlines. - - Useful when doing operations across the headline hierarchy - """ - return self.headlines - ## Querying def get_links(self): for headline in self.headlines: @@ -2560,6 +2526,9 @@ class OrgDoc: for struct in self.structural: lines.append(dump_structural(struct)) + for content in self.delimiters: + lines.append(dump_delimiters(content)) + for kw in self.keywords: lines.append(dump_kw(kw)) @@ -2597,6 +2566,7 @@ class OrgDocReader: self.list_items, self.structural, self.properties, + self.delimiters, self.environment, ) diff --git a/org_rw/utils.py b/org_rw/utils.py index 5b8b4e5..87f6712 100644 --- a/org_rw/utils.py +++ b/org_rw/utils.py @@ -9,6 +9,7 @@ from .org_rw import ( ListItem, RawLine, Strike, + TableRow, Text, Underlined, Verbatim, @@ -50,6 +51,8 @@ def get_raw_contents(doc) -> str: return doc.get_raw() if isinstance(doc, ListItem): return dump_contents(doc)[1] + if isinstance(doc, TableRow): + return dump_contents(doc)[1] print("Unhandled type: " + str(doc)) raise NotImplementedError("Unhandled type: " + str(doc)) diff --git a/requirements.txt b/requirements.txt deleted file mode 100644 index 1c51c66..0000000 --- a/requirements.txt +++ /dev/null @@ -1 +0,0 @@ -# No external requirements at this point diff --git a/tests/test_org.py b/tests/test_org.py index 59441d5..a1fdff1 100644 --- a/tests/test_org.py +++ b/tests/test_org.py @@ -1024,171 +1024,6 @@ class TestSerde(unittest.TestCase): self.assertEqual(dumps(doc), "* TODO First entry") - def test_refile_headline_down_to_bottom(self) -> None: - orig = """* Source Headline -** Child of Source -* Destination Headline -** Existing Child""" - doc = loads(orig) - - source_headline = doc.headlines[0] - destination_headline = doc.headlines[1] - - result = source_headline.refile(destination_headline) - - assert result == destination_headline - assert source_headline.parent == destination_headline - assert source_headline in destination_headline.children - assert destination_headline.children[-1] == source_headline - assert ( - dumps(doc) - == """* Destination Headline -** Existing Child -** Source Headline -*** Child of Source""" - ) - - def test_refile_headline_down_to_top(self) -> None: - orig = """* Source Headline -** Child of Source -* Destination Headline -** Existing Child""" - doc = loads(orig) - - source_headline = doc.headlines[0] - destination_headline = doc.headlines[1] - - result = source_headline.refile(destination_headline, top=True) - - assert result == destination_headline - assert source_headline.parent == destination_headline - assert source_headline in destination_headline.children - assert destination_headline.children[0] == source_headline - assert ( - dumps(doc) - == """* Destination Headline -** Source Headline -*** Child of Source -** Existing Child""" - ) - - def test_refile_headline_down_to_existing_child(self) -> None: - orig = """* Source Headline -** Child of Source -* Destination Parent -** Destination Headline""" - doc = loads(orig) - - source_headline = doc.headlines[0] - destination_headline = doc.headlines[1] - destination_child = destination_headline.children[0] - - result = source_headline.refile(destination_child) - - assert result == destination_child - assert source_headline.parent == destination_child - assert source_headline in destination_child.children - assert destination_child.children[-1] == source_headline - assert ( - dumps(doc) - == """* Destination Parent -** Destination Headline -*** Source Headline -**** Child of Source""" - ) - - def test_refile_headline_from_child_to_parent_bottom(self) -> None: - orig = """* Destination Headline -** Existing Child -*** Source Headline -**** Source Child""" - doc = loads(orig) - source_headline = doc.headlines[0].children[0].children[0] - destination_headline = doc.headlines[0] - - result = source_headline.refile(destination_headline) - - assert result == destination_headline - assert source_headline.parent == destination_headline - assert source_headline in destination_headline.children - assert destination_headline.children[-1] == source_headline - assert ( - dumps(doc) - == """* Destination Headline -** Existing Child -** Source Headline -*** Source Child""" - ) - - def test_refile_headline_from_child_to_parent_top(self) -> None: - orig = """* Destination Headline -** Existing Child -*** Source Headline -**** Source Child""" - doc = loads(orig) - source_headline = doc.headlines[0].children[0].children[0] - destination_headline = doc.headlines[0] - - result = source_headline.refile(destination_headline, top=True) - - assert result == destination_headline - assert source_headline.parent == destination_headline - assert source_headline in destination_headline.children - assert destination_headline.children[0] == source_headline - assert ( - dumps(doc) - == """* Destination Headline -** Source Headline -*** Source Child -** Existing Child""" - ) - - def test_refile_headline_from_child_to_first_level_at_bottom(self) -> None: - orig = """* Destination Headline -** Existing Child -*** Source Headline -**** Source Child""" - doc = loads(orig) - source_headline = doc.headlines[0].children[0].children[0] - destination_headline = doc.headlines[0].parent - - result = source_headline.refile(destination_headline) - - assert result == destination_headline - assert source_headline.parent == destination_headline - assert source_headline in destination_headline.children - assert destination_headline.children[-1] == source_headline - assert ( - dumps(doc) - == """* Destination Headline -** Existing Child -* Source Headline -** Source Child""" - ) - - def test_refile_headline_from_child_to_first_level_at_top(self) -> None: - orig = """* Destination Headline -** Existing Child -*** Source Headline -**** Source Child""" - doc = loads(orig) - source_headline = doc.headlines[0].children[0].children[0] - destination_headline = doc.headlines[0].parent - - result = source_headline.refile(destination_headline, top=True) - - assert result == destination_headline - assert source_headline.parent == destination_headline - assert source_headline in destination_headline.children - assert destination_headline.children[0] == source_headline - assert ( - dumps(doc) - == """* Source Headline -** Source Child -* Destination Headline -** Existing Child""" - ) - def print_tree(tree, indentation=0, headline=None): for element in tree: