Struct binjs_io::entropy::dictionary::DictionaryBuilder

pub struct DictionaryBuilder { /* fields omitted */ }

A structure used to build a dictionary based on a sample of files.

Methods

impl DictionaryBuilder

pub fn new(options: Options) -> Self

Create a new dictionary builder using paths of depth depth and windows of width width.

Use DictionaryBuilder::done to convert it into a Dictionary.

pub fn done(self, threshold: FilesContaining) -> DictionaryFamily<Instances>

Return a dictionary containing all the paths collected and all the user-extensible content that appear in more than one file.

pub fn len(&self) -> usize

pub fn files_containing(&self) -> &UserExtensibleData<FilesContaining>

Access statistics on the number of files containing specific user-extensible values.

pub fn instances_in_file(&self) -> &UserExtensibleData<InstancesInFile>

Access statistics on the number of instances of a specific user-extensible value.

Trait Implementations

impl<'a> TokenWriter for &'a mut DictionaryBuilder

type Data = [u8; 0]

The type of data generated by this writer. Typically some variant of Vec<u8>.

fn done(self) -> Result<Self::Data, TokenWriterError>

Finish writing, produce data.

fn bool_at(
    &mut self,
    value: Option<bool>,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write single bool.

fn float_at(
    &mut self,
    value: Option<f64>,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a single number.

fn unsigned_long_at(
    &mut self,
    value: u32,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a single u32.

fn string_enum_at(
    &mut self,
    value: &SharedString,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a single UTF-8 value from a string enumeration.

fn string_at(
    &mut self,
    value: Option<&SharedString>,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a single UTF-8 string.

fn property_key_at(
    &mut self,
    value: Option<&PropertyKey>,
    path: &IOPath
) -> Result<(), TokenWriterError>

fn identifier_name_at(
    &mut self,
    value: Option<&IdentifierName>,
    path: &IOPath
) -> Result<(), TokenWriterError>

fn enter_list_at(
    &mut self,
    len: usize,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a list.

fn enter_tagged_tuple_at(
    &mut self,
    node: &dyn Node,
    tag: &InterfaceName,
    children: &[&FieldName],
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a tagged tuple.

fn offset_at(&mut self, path: &IOPath) -> Result<(), TokenWriterError>

Write the number of bytes left in this tuple.

fn enter_scoped_dictionary_at(
    &mut self,
    name: &SharedString,
    path: &IOPath
) -> Result<(), TokenWriterError>

Signal that, from this point, writing is expected to use a specialized dictionary. Use of the specialized dictionary will stop at exit_scoped_dictionary_at.

fn exit_scoped_dictionary_at(
    &mut self,
    name: &SharedString,
    path: &IOPath
) -> Result<(), TokenWriterError>

Signal that, from this point, writing is expected to return to the previous specialized dictionary.

fn exit_tagged_tuple_at(
    &mut self,
    _node: &dyn Node,
    _tag: &InterfaceName,
    _children: &[&FieldName],
    _path: &Path
) -> Result<(), TokenWriterError>

fn exit_list_at(&mut self, _path: &Path) -> Result<(), TokenWriterError>

impl TokenWriter for DictionaryBuilder

type Data = [u8; 0]

The type of data generated by this writer. Typically some variant of Vec<u8>.

fn done(self) -> Result<Self::Data, TokenWriterError>

Finish writing, produce data.

fn bool_at(
    &mut self,
    value: Option<bool>,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write single bool.

fn float_at(
    &mut self,
    value: Option<f64>,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a single number.

fn unsigned_long_at(
    &mut self,
    value: u32,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a single u32.

fn string_enum_at(
    &mut self,
    value: &SharedString,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a single UTF-8 value from a string enumeration.

fn string_at(
    &mut self,
    value: Option<&SharedString>,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a single UTF-8 string.

fn property_key_at(
    &mut self,
    value: Option<&PropertyKey>,
    path: &IOPath
) -> Result<(), TokenWriterError>

fn identifier_name_at(
    &mut self,
    value: Option<&IdentifierName>,
    path: &IOPath
) -> Result<(), TokenWriterError>

fn enter_list_at(
    &mut self,
    len: usize,
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a list.

fn enter_tagged_tuple_at(
    &mut self,
    _node: &dyn Node,
    tag: &InterfaceName,
    _children: &[&FieldName],
    path: &IOPath
) -> Result<(), TokenWriterError>

Write a tagged tuple.

fn offset_at(&mut self, _path: &IOPath) -> Result<(), TokenWriterError>

Write the number of bytes left in this tuple.

fn enter_scoped_dictionary_at(
    &mut self,
    name: &SharedString,
    _path: &IOPath
) -> Result<(), TokenWriterError>

Signal that, from this point, writing is expected to use a specialized dictionary. Use of the specialized dictionary will stop at exit_scoped_dictionary_at.

fn exit_scoped_dictionary_at(
    &mut self,
    name: &SharedString,
    _path: &IOPath
) -> Result<(), TokenWriterError>

Signal that, from this point, writing is expected to return to the previous specialized dictionary.

fn exit_tagged_tuple_at(
    &mut self,
    _node: &dyn Node,
    _tag: &InterfaceName,
    _children: &[&FieldName],
    _path: &Path
) -> Result<(), TokenWriterError>

fn exit_list_at(&mut self, _path: &Path) -> Result<(), TokenWriterError>