from streamer.parse import StreamFile, parse_markdown_file, Shard
from faker import Faker

fake = Faker()


class TestParseProcess:
    file_name: str = fake.file_name(extension="md")

    def test_parse_empty_file(self):
        assert parse_markdown_file(self.file_name, "") == StreamFile(
            filename=self.file_name, shard=None
        )

    def test_parse_basic_one_line_file(self):
        test_file = "Hello World"
        assert parse_markdown_file(self.file_name, test_file) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=[],
                tags=[],
                start_line=1,
                end_line=1,
                children=[],
            ),
        )

    def test_parse_basic_multi_line_file(self):
        test_file = "Hello World\n\nHello again!"
        assert parse_markdown_file(self.file_name, test_file) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=[],
                tags=[],
                start_line=1,
                end_line=3,
                children=[],
            ),
        )

    def test_parse_single_line_with_tag(self):
        test_file = "@Tag Hello World"
        assert parse_markdown_file(self.file_name, test_file) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=["Tag"],
                tags=[],
                start_line=1,
                end_line=1,
                children=[],
            ),
        )

    def test_parse_single_line_with_two_tags(self):
        test_file = "@Tag1 @Tag2 Hello World"
        assert parse_markdown_file(self.file_name, test_file) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=["Tag1", "Tag2"],
                tags=[],
                start_line=1,
                end_line=1,
                children=[],
            ),
        )

    def test_parse_single_line_with_two_tags_and_misplaced_tag(self):
        test_file = "@Tag1 @Tag2 Hello World @Tag3"
        assert parse_markdown_file(self.file_name, test_file) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=["Tag1", "Tag2"],
                tags=["Tag3"],
                start_line=1,
                end_line=1,
                children=[],
            ),
        )

    def test_parse_split_paragraphs_into_shards(self):
        file_text = "Hello World!\n\n@Tag1 Block 1\n\n@Tag2 Block 2"

        assert parse_markdown_file(self.file_name, file_text) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=[],
                tags=[],
                start_line=1,
                end_line=5,
                children=[
                    Shard(
                        markers=["Tag1"],
                        tags=[],
                        start_line=3,
                        end_line=3,
                        children=[],
                    ),
                    Shard(
                        markers=["Tag2"],
                        tags=[],
                        start_line=5,
                        end_line=5,
                        children=[],
                    ),
                ],
            ),
        )

    def test_parse_split_paragraph_with_inner_tags_at_more_positions(self):
        file_text = "Hello @Tag1 World!\n\n@Marker Block 1\n\nBlock 2 @Tag2"

        assert parse_markdown_file(self.file_name, file_text) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=[],
                tags=["Tag1", "Tag2"],
                start_line=1,
                end_line=5,
                children=[
                    Shard(
                        markers=["Marker"],
                        tags=[],
                        start_line=3,
                        end_line=3,
                        children=[],
                    ),
                ],
            ),
        )

    def test_parse_header_without_markers(self):
        file_text = "# Heading\n\n## Subheading"

        assert parse_markdown_file(self.file_name, file_text) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=[],
                tags=[],
                start_line=1,
                end_line=3,
                children=[],
            ),
        )

    def test_parse_split_at_heading_if_marker_on_subheading(self):
        file_text = "# Heading @Tag1\n\n## @Marker1 Subheading @Tag2\n\n# Heading @Tag3"

        assert parse_markdown_file(self.file_name, file_text) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=[],
                tags=[],
                start_line=1,
                end_line=5,
                children=[
                    Shard(
                        markers=[],
                        tags=["Tag1"],
                        start_line=1,
                        end_line=4,
                        children=[
                            Shard(
                                markers=["Marker1"],
                                tags=["Tag2"],
                                start_line=3,
                                end_line=4,
                                children=[],
                            ),
                        ],
                    ),
                    Shard(
                        markers=[], tags=["Tag3"], start_line=5, end_line=5, children=[]
                    ),
                ],
            ),
        )

    def test_parse_only_parse_releveant_levels(self):
        file_text = "# @Marker1 Heading @Tag1\n\n## Subheading @Tag2"

        assert parse_markdown_file(self.file_name, file_text) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=["Marker1"],
                tags=["Tag1", "Tag2"],
                start_line=1,
                end_line=3,
                children=[],
            ),
        )

    def test_continue_full_parsing_before_headings_start(self):
        file_text = "Hello\n\n@Marker1 World!\n\n# @Marker2 I'm a heading!"

        assert parse_markdown_file(self.file_name, file_text) == StreamFile(
            filename=self.file_name,
            shard=Shard(
                markers=[],
                tags=[],
                start_line=1,
                end_line=5,
                children=[
                    Shard(
                        markers=["Marker1"],
                        tags=[],
                        start_line=3,
                        end_line=3,
                        children=[],
                    ),
                    Shard(
                        markers=["Marker2"],
                        tags=[],
                        start_line=5,
                        end_line=5,
                        children=[],
                    ),
                ],
            ),
        )