diff options
Diffstat (limited to 'libcpp')
-rw-r--r-- | libcpp/charset.c | 98 | ||||
-rw-r--r-- | libcpp/include/cpplib.h | 40 | ||||
-rw-r--r-- | libcpp/init.c | 1 |
3 files changed, 101 insertions, 38 deletions
diff --git a/libcpp/charset.c b/libcpp/charset.c index db47235..28b81c9c 100644 --- a/libcpp/charset.c +++ b/libcpp/charset.c @@ -2276,49 +2276,90 @@ cpp_string_location_reader::get_next () return result; } -/* Helper for cpp_byte_column_to_display_column and its inverse. Given a - pointer to a UTF-8-encoded character, compute its display width. *INBUFP - points on entry to the start of the UTF-8 encoding of the character, and - is updated to point just after the last byte of the encoding. *INBYTESLEFTP - contains on entry the remaining size of the buffer into which *INBUFP - points, and this is also updated accordingly. If *INBUFP does not +cpp_display_width_computation:: +cpp_display_width_computation (const char *data, int data_length, int tabstop) : + m_begin (data), + m_next (m_begin), + m_bytes_left (data_length), + m_tabstop (tabstop), + m_display_cols (0) +{ + gcc_assert (m_tabstop > 0); +} + + +/* The main implementation function for class cpp_display_width_computation. + m_next points on entry to the start of the UTF-8 encoding of the next + character, and is updated to point just after the last byte of the encoding. + m_bytes_left contains on entry the remaining size of the buffer into which + m_next points, and this is also updated accordingly. If m_next does not point to a valid UTF-8-encoded sequence, then it will be treated as a single - byte with display width 1. */ + byte with display width 1. m_cur_display_col is the current display column, + relative to which tab stops should be expanded. Returns the display width of + the codepoint just processed. */ -static inline int -compute_next_display_width (const uchar **inbufp, size_t *inbytesleftp) +int +cpp_display_width_computation::process_next_codepoint () { cppchar_t c; - if (one_utf8_to_cppchar (inbufp, inbytesleftp, &c) != 0) + int next_width; + + if (*m_next == '\t') + { + ++m_next; + --m_bytes_left; + next_width = m_tabstop - (m_display_cols % m_tabstop); + } + else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c) + != 0) { /* Input is not convertible to UTF-8. This could be fine, e.g. in a string literal, so don't complain. Just treat it as if it has a width of one. */ - ++*inbufp; - --*inbytesleftp; - return 1; + ++m_next; + --m_bytes_left; + next_width = 1; + } + else + { + /* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */ + next_width = cpp_wcwidth (c); } - /* one_utf8_to_cppchar() has updated inbufp and inbytesleftp for us. */ - return cpp_wcwidth (c); + m_display_cols += next_width; + return next_width; +} + +/* Utility to advance the byte stream by the minimum amount needed to consume + N display columns. Returns the number of display columns that were + actually skipped. This could be less than N, if there was not enough data, + or more than N, if the last character to be skipped had a sufficiently large + display width. */ +int +cpp_display_width_computation::advance_display_cols (int n) +{ + const int start = m_display_cols; + const int target = start + n; + while (m_display_cols < target && !done ()) + process_next_codepoint (); + return m_display_cols - start; } /* For the string of length DATA_LENGTH bytes that begins at DATA, compute how many display columns are occupied by the first COLUMN bytes. COLUMN may exceed DATA_LENGTH, in which case the phantom bytes at the end are - treated as if they have display width 1. */ + treated as if they have display width 1. Tabs are expanded to the next tab + stop, relative to the start of DATA. */ int cpp_byte_column_to_display_column (const char *data, int data_length, - int column) + int column, int tabstop) { - int display_col = 0; - const uchar *udata = (const uchar *) data; const int offset = MAX (0, column - data_length); - size_t inbytesleft = column - offset; - while (inbytesleft) - display_col += compute_next_display_width (&udata, &inbytesleft); - return display_col + offset; + cpp_display_width_computation dw (data, column - offset, tabstop); + while (!dw.done ()) + dw.process_next_codepoint (); + return dw.display_cols_processed () + offset; } /* For the string of length DATA_LENGTH bytes that begins at DATA, compute @@ -2328,14 +2369,11 @@ cpp_byte_column_to_display_column (const char *data, int data_length, int cpp_display_column_to_byte_column (const char *data, int data_length, - int display_col) + int display_col, int tabstop) { - int column = 0; - const uchar *udata = (const uchar *) data; - size_t inbytesleft = data_length; - while (column < display_col && inbytesleft) - column += compute_next_display_width (&udata, &inbytesleft); - return data_length - inbytesleft + MAX (0, display_col - column); + cpp_display_width_computation dw (data, data_length, tabstop); + const int avail_display = dw.advance_display_cols (display_col); + return dw.bytes_processed () + MAX (0, display_col - avail_display); } /* Our own version of wcwidth(). We don't use the actual wcwidth() in glibc, diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index e8bb15d..8e39886 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -312,9 +312,6 @@ enum cpp_normalize_level { carries all the options visible to the command line. */ struct cpp_options { - /* Characters between tab stops. */ - unsigned int tabstop; - /* The language we're preprocessing. */ enum c_lang lang; @@ -1335,14 +1332,43 @@ extern const char * cpp_get_userdef_suffix (const cpp_token *); /* In charset.c */ + +/* A class to manage the state while converting a UTF-8 sequence to cppchar_t + and computing the display width one character at a time. */ +class cpp_display_width_computation { + public: + cpp_display_width_computation (const char *data, int data_length, + int tabstop); + const char *next_byte () const { return m_next; } + int bytes_processed () const { return m_next - m_begin; } + int bytes_left () const { return m_bytes_left; } + bool done () const { return !bytes_left (); } + int display_cols_processed () const { return m_display_cols; } + + int process_next_codepoint (); + int advance_display_cols (int n); + + private: + const char *const m_begin; + const char *m_next; + size_t m_bytes_left; + const int m_tabstop; + int m_display_cols; +}; + +/* Convenience functions that are simple use cases for class + cpp_display_width_computation. Tab characters will be expanded to spaces + as determined by TABSTOP. */ int cpp_byte_column_to_display_column (const char *data, int data_length, - int column); -inline int cpp_display_width (const char *data, int data_length) + int column, int tabstop); +inline int cpp_display_width (const char *data, int data_length, + int tabstop) { - return cpp_byte_column_to_display_column (data, data_length, data_length); + return cpp_byte_column_to_display_column (data, data_length, data_length, + tabstop); } int cpp_display_column_to_byte_column (const char *data, int data_length, - int display_col); + int display_col, int tabstop); int cpp_wcwidth (cppchar_t c); #endif /* ! LIBCPP_CPPLIB_H */ diff --git a/libcpp/init.c b/libcpp/init.c index d641d0a1..0aac5ac 100644 --- a/libcpp/init.c +++ b/libcpp/init.c @@ -190,7 +190,6 @@ cpp_create_reader (enum c_lang lang, cpp_hash_table *table, CPP_OPTION (pfile, discard_comments) = 1; CPP_OPTION (pfile, discard_comments_in_macro_exp) = 1; CPP_OPTION (pfile, max_include_depth) = 200; - CPP_OPTION (pfile, tabstop) = 8; CPP_OPTION (pfile, operator_names) = 1; CPP_OPTION (pfile, warn_trigraphs) = 2; CPP_OPTION (pfile, warn_endif_labels) = 1; |