features-supported.sgml features-unsupported.sgml errcodes-table.sgml \
keywords-table.sgml targets-meson.sgml wait_event_types.sgml
-ALLSGML := $(wildcard $(srcdir)/*.sgml $(srcdir)/ref/*.sgml) $(GENERATED_SGML)
+ALL_SGML := $(wildcard $(srcdir)/*.sgml $(srcdir)/ref/*.sgml) $(GENERATED_SGML)
ALL_IMAGES := $(wildcard $(srcdir)/images/*.svg)
# we're at it, also resolve all entities (that is, copy all included
# files into one big file). This helps tools that don't understand
# vpath builds (such as dbtoepub).
-postgres-full.xml: postgres.sgml $(ALLSGML)
+postgres-full.xml: postgres.sgml $(ALL_SGML)
$(XMLLINT) $(XMLINCLUDE) --output $@ --noent --valid $<
## Print
##
-postgres.pdf:
+postgres.pdf pdf:
$(error Invalid target; use postgres-A4.pdf or postgres-US.pdf as targets)
XSLTPROC_FO_FLAGS += --stringparam img.src.path '$(srcdir)/'
+# XSL Formatting Objects (FO), https://en.wikipedia.org/wiki/XSL_Formatting_Objects
%-A4.fo: stylesheet-fo.xsl %-full.xml
$(XSLTPROC) $(XMLINCLUDE) $(XSLTPROCFLAGS) $(XSLTPROC_FO_FLAGS) --stringparam paper.type A4 -o $@ $^
##
# Quick syntax check without style processing
-check: postgres.sgml $(ALLSGML) check-tabs check-nbsp
+check: postgres.sgml $(ALL_SGML) check-tabs check-nbsp
$(XMLLINT) $(XMLINCLUDE) --noout --valid $<
# Use perl command because non-GNU grep or sed could not have hex escape sequence.
check-nbsp:
@ ( $(PERL) -ne '/\xC2\xA0/ and print("$$ARGV:$$_"),$$n++; END {exit($$n>0)}' \
- $(wildcard $(srcdir)/*.sgml $(srcdir)/ref/*.sgml $(srcdir)/*.xsl) ) || \
+ $(wildcard $(srcdir)/*.sgml $(srcdir)/ref/*.sgml $(srcdir)/images/*.svg $(srcdir)/*.xsl $(srcdir)/images/*.xsl) ) || \
(echo "Non-breaking spaces appear in SGML/XML files" 1>&2; exit 1)
##
--- /dev/null
+<!-- doc/src/sgml/README.non-ASCII -->
+
+Representation of non-ASCII characters
+--------------------------------------
+
+Find non-ASCII characters using:
+
+ grep --recursive --color='auto' -P '[\x80-\xFF]' .
+
+Convert to HTML4 named entity (&) escapes
+-----------------------------------------
+
+We support several output formats:
+
+* html (supports all Unicode characters)
+* man (supports all Unicode characters)
+* pdf (supports only Latin-1 characters)
+* info
+
+While some output formatting tools support all Unicode characters,
+others only support Latin-1 characters. Specifically, the PDF rendering
+engine can only display Latin-1 characters; non-Latin-1 Unicode
+characters are displayed as "###".
+
+Therefore, in the SGML files, we only use Latin-1 characters. We
+typically encode these characters as HTML entities, e.g., Álvaro.
+It is also possible to safely represent Latin-1 characters in UTF8
+encoding for all output formats.
+
+Do not use UTF numeric character escapes (&#nnn;).
+
+HTML entities
+ official: http://www.w3.org/TR/html4/sgml/entities.html
+ one page: http://www.zipcon.net/~swhite/docs/computers/browsers/entities_page.html
+ other lists: http://www.zipcon.net/~swhite/docs/computers/browsers/entities.html
+ http://www.zipcon.net/~swhite/docs/computers/browsers/entities_page.html
+ https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references
<programlisting>
-- ignore differences in accents and case
CREATE COLLATION ignore_accent_case (provider = icu, deterministic = false, locale = 'und-u-ks-level1');
-SELECT 'Å' = 'A' COLLATE ignore_accent_case; -- true
+SELECT 'Å' = 'A' COLLATE ignore_accent_case; -- true
SELECT 'z' = 'Z' COLLATE ignore_accent_case; -- true
-- upper case letters sort before lower case.
<entry><literal>'ab' = U&'a\2063b'</literal></entry>
<entry><literal>'x-y' = 'x_y'</literal></entry>
<entry><literal>'g' = 'G'</literal></entry>
- <entry><literal>'n' = 'ñ'</literal></entry>
+ <entry><literal>'n' = 'ñ'</literal></entry>
<entry><literal>'y' = 'z'</literal></entry>
</row>
</thead>
<para>
At every level, even with full normalization off, basic normalization is
- performed. For example, <literal>'á'</literal> may be composed of the
+ performed. For example, <literal>'á'</literal> may be composed of the
code points <literal>U&'\0061\0301'</literal> or the single code
point <literal>U&'\00E1'</literal>, and those sequences will be
considered equal even at the <literal>identic</literal> level. To treat
<entry><literal>false</literal></entry>
<entry>
Backwards comparison for the level 2 differences. For example,
- locale <literal>und-u-kb</literal> sorts <literal>'àe'</literal>
- before <literal>'aé'</literal>.
+ locale <literal>und-u-kb</literal> sorts <literal>'àe'</literal>
+ before <literal>'aé'</literal>.
</entry>
</row>
<title>a4->end</title>
<path fill="none" stroke="#000000" d="M259,-312.5834C259,-312.5834 259,-54.659 259,-54.659"/>
<polygon fill="#000000" stroke="#000000" points="262.5001,-54.659 259,-44.659 255.5001,-54.6591 262.5001,-54.659"/>
-<text text-anchor="middle" x="246" y="-186.6212" font-family="sans-serif" font-size="10.00" fill="#000000">true </text>
+<text text-anchor="middle" x="246" y="-186.6212" font-family="sans-serif" font-size="10.00" fill="#000000">true</text>
</g>
<!-- a5 -->
<g id="node7" class="node">
<title>a4->a5</title>
<path fill="none" stroke="#000000" d="M144,-298.269C144,-298.269 144,-286.5248 144,-286.5248"/>
<polygon fill="#000000" stroke="#000000" points="147.5001,-286.5248 144,-276.5248 140.5001,-286.5249 147.5001,-286.5248"/>
-<text text-anchor="middle" x="127" y="-284.3969" font-family="sans-serif" font-size="10.00" fill="#000000">false </text>
+<text text-anchor="middle" x="127" y="-284.3969" font-family="sans-serif" font-size="10.00" fill="#000000">false</text>
</g>
<!-- a6 -->
<g id="node8" class="node">
\<[a-z]+_[a-z_]+\> <varname>, <structfield>
<systemitem class="osname">
-non-ASCII characters find using grep -P '[\x80-\xFF]' or
- (remove 'X') grep -X-color='auto' -P -n "[\x80-\xFF]"
- convert to HTML4 named entity (&) escapes
-
- official: http://www.w3.org/TR/html4/sgml/entities.html
- one page: http://www.zipcon.net/~swhite/docs/computers/browsers/entities_page.html
- other lists: http://www.zipcon.net/~swhite/docs/computers/browsers/entities.html
- http://www.zipcon.net/~swhite/docs/computers/browsers/entities_page.html
- https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references
-
- We cannot use UTF8 because rendering engines have to
- support the referenced characters.
-
- Do not use numeric _UTF_ numeric character escapes (&#nnn;),
- we can only use Latin1.
-
- Example: Alvaro Herrera is Álvaro Herrera
-
wrap long lines
For new features, add links to the documentation sections.
<!-- Slight rephrasing to indicate that missing sections are found
in the documentation. -->
<l:context name="xref-number-and-title">
- <l:template name="chapter" text="Chapter %n, %t, in the documentation"/>
- <l:template name="sect1" text="Section %n, “%t”, in the documentation"/>
- <l:template name="sect2" text="Section %n, “%t”, in the documentation"/>
- <l:template name="sect3" text="Section %n, “%t”, in the documentation"/>
- <l:template name="sect4" text="Section %n, “%t”, in the documentation"/>
- <l:template name="sect5" text="Section %n, “%t”, in the documentation"/>
+ <l:template name="chapter" text="Chapter %n, "%t", in the documentation"/>
+ <l:template name="sect1" text="Section %n, "%t", in the documentation"/>
+ <l:template name="sect2" text="Section %n, "%t", in the documentation"/>
+ <l:template name="sect3" text="Section %n, "%t", in the documentation"/>
+ <l:template name="sect4" text="Section %n, "%t", in the documentation"/>
+ <l:template name="sect5" text="Section %n, "%t", in the documentation"/>
</l:context>
</l:l10n>
</l:i18n>
projects / postgresql.git / commitdiff
